Triple
T574731
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SIGKDD |
E13737
|
entity |
| Predicate | flagshipEvent |
P6628
|
FINISHED |
| Object |
KDD conference
The KDD conference is a premier international research conference focused on knowledge discovery and data mining, bringing together experts in data science, machine learning, and big data.
|
E13737
|
NE FINISHED |
How this triple was built (5 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: KDD conference | Statement: [SIGKDD, flagshipEvent, KDD conference]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: KDD conference Context triple: [SIGKDD, flagshipEvent, KDD conference]
-
A.
SIGKDD
SIGKDD is the ACM Special Interest Group on Knowledge Discovery and Data Mining, best known for its flagship KDD conference and contributions to data mining and machine learning research.
-
B.
ACM Transactions on Knowledge Discovery from Data
ACM Transactions on Knowledge Discovery from Data is a peer-reviewed scholarly journal published by the Association for Computing Machinery that focuses on research in data mining, knowledge discovery, and related areas of data science and machine learning.
-
C.
ACM Transactions on Data Science
ACM Transactions on Data Science is a peer-reviewed scholarly journal published by the Association for Computing Machinery that focuses on research in data science, including theory, methods, and applications.
-
D.
SIGKDD Innovation Award
The SIGKDD Innovation Award is a premier annual honor in the data mining and knowledge discovery community recognizing influential, long-lasting technical contributions to the field.
-
E.
SIGKDD Service Award
The SIGKDD Service Award is a prestigious annual honor recognizing individuals who have made exceptional contributions to the data mining and knowledge discovery community through dedicated professional service and leadership.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: KDD conference Triple: [SIGKDD, flagshipEvent, KDD conference]
Generated description
The KDD conference is a premier international research conference focused on knowledge discovery and data mining, bringing together experts in data science, machine learning, and big data.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: KDD conference Target entity description: The KDD conference is a premier international research conference focused on knowledge discovery and data mining, bringing together experts in data science, machine learning, and big data.
-
A.
SIGKDD
chosen
SIGKDD is the ACM Special Interest Group on Knowledge Discovery and Data Mining, best known for its flagship KDD conference and contributions to data mining and machine learning research.
-
B.
ACM Transactions on Knowledge Discovery from Data
ACM Transactions on Knowledge Discovery from Data is a peer-reviewed scholarly journal published by the Association for Computing Machinery that focuses on research in data mining, knowledge discovery, and related areas of data science and machine learning.
-
C.
ACM Transactions on Data Science
ACM Transactions on Data Science is a peer-reviewed scholarly journal published by the Association for Computing Machinery that focuses on research in data science, including theory, methods, and applications.
-
D.
SIGKDD Innovation Award
The SIGKDD Innovation Award is a premier annual honor in the data mining and knowledge discovery community recognizing influential, long-lasting technical contributions to the field.
-
E.
SIGKDD Service Award
The SIGKDD Service Award is a prestigious annual honor recognizing individuals who have made exceptional contributions to the data mining and knowledge discovery community through dedicated professional service and leadership.
- F. None of above.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: flagshipEvent Context triple: [SIGKDD, flagshipEvent, KDD conference]
-
A.
flagshipFor
Indicates that one entity serves as the primary or leading representative example for another entity, often embodying its most important qualities or status.
-
B.
flagshipProgram
Indicates that a program is the primary, most prominent, or most important offering associated with an entity.
-
C.
flagshipPeriod
Indicates the time span during which an entity serves as the primary or leading representative (flagship) within a given context or organization.
-
D.
flagshipStatus
Indicates that an entity holds the primary or most prominent position within a group, organization, or collection, often serving as its leading or representative example.
-
E.
featuresEvent
chosen
Indicates that an entity includes, presents, or highlights a particular event as part of its content or offering.
- F. None of above.
Provenance (6 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69a4933fa4d88190a7949cc83c08c5c1 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49b4c23548190a3b883239c7c78c8 |
completed | March 1, 2026, 8:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a50e23bce481908404040b848ba9c1 |
completed | March 2, 2026, 4:12 a.m. |
| NEDg | Description generation | batch_69a50ed652148190a84c0d2aa5307211 |
completed | March 2, 2026, 4:15 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a50f53c16c8190bbeb7fa550ed46b1 |
completed | March 2, 2026, 4:17 a.m. |
| PD | Predicate disambiguation | batch_69a494c4969c819080375d08f9eec50c |
completed | March 1, 2026, 7:34 p.m. |
Created at: March 1, 2026, 7:33 p.m.