Triple
T15160641
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | VLDB Best Paper Award |
E362204
|
entity |
| Predicate | presentedAt |
P3021
|
FINISHED |
| Object | Very Large Data Bases conference |
E1104719
|
NE FINISHED |
How this triple was built (2 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: Very Large Data Bases conference | Statement: [VLDB Best Paper Award, presentedAt, Very Large Data Bases conference]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Very Large Data Bases conference Context triple: [VLDB Best Paper Award, presentedAt, Very Large Data Bases conference]
-
A.
VLDB Conference
chosen
The VLDB Conference is a leading international research conference focused on database management, data engineering, and large-scale data systems.
-
B.
ACM SIGMOD Conference
The ACM SIGMOD Conference is a premier annual international research conference focusing on the management of data and database systems, organized by the ACM Special Interest Group on Management of Data.
-
C.
IEEE International Conference on Data Engineering
The IEEE International Conference on Data Engineering is a leading annual research conference focused on advances in data management, database systems, and related engineering technologies.
-
D.
VLDB Endowment
The VLDB Endowment is the non-profit organization that oversees and supports the Very Large Data Bases (VLDB) community, including its flagship conferences and associated awards in the database research field.
-
E.
ACM SIGMOD Symposium on Principles of Database Systems
The ACM SIGMOD Symposium on Principles of Database Systems (PODS) is a leading annual research conference focused on the theoretical foundations and formal aspects of database systems.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d85a087b7c81908baa94a53dac8d68 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e0060f2efc8190aa0eb5fb8d4ce085 |
completed | April 15, 2026, 9:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69febffc94e48190844e226c245a9ce3 |
completed | May 9, 2026, 5:02 a.m. |
Created at: April 10, 2026, 3:08 a.m.