Triple
T29913637
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | attempted to vote for John Kasich for president in 2016 |
E759734
|
entity |
| Predicate | candidateIntended |
P88492
|
FINISHED |
| Object |
John Kasich
John Kasich is an American politician and former governor of Ohio who sought the Republican nomination for president in 2016.
|
E1893281
|
NE FINISHED |
How this triple was built (3 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: John Kasich | Statement: [attempted to vote for John Kasich for president in 2016, candidateIntended, John Kasich]
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: John Kasich Triple: [attempted to vote for John Kasich for president in 2016, candidateIntended, John Kasich]
Generated description
John Kasich is an American politician and former governor of Ohio who sought the Republican nomination for president in 2016.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: candidateIntended Context triple: [attempted to vote for John Kasich for president in 2016, candidateIntended, John Kasich]
-
A.
candidateFor
Indicates that one entity is being considered or proposed as a possible choice, option, or selection for another entity (such as a role, position, or outcome).
-
B.
targetCandidate
Indicates that an entity is being considered or designated as a potential target for selection, action, or further evaluation.
-
C.
intendsTo
chosen
Indicates that one entity has the purpose, plan, or desire to perform an action involving another entity or outcome.
-
D.
candidateType
Indicates the classification or category assigned to a candidate within a given context or process.
-
E.
candidateIdentifiedAs
Indicates that a particular individual or option has been recognized or designated as the specific candidate in question.
- 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_69f2246189fc8190996b63ee1f9a2374 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f6775c80548190bd6329cb919a921c |
completed | May 2, 2026, 10:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2714147dc481909c8440875cad5073 |
completed | June 8, 2026, 7:12 p.m. |
| NEDg | Description generation | batch_6a271498c12c81909a3ca72cfeb8bcb5 |
completed | June 8, 2026, 7:14 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a2719a575388190baec154da1d3ed1a |
completed | June 8, 2026, 7:36 p.m. |
| PD | Predicate disambiguation | batch_69f66ec8298c8190b41fe9d182c05676 |
completed | May 2, 2026, 9:38 p.m. |
Created at: April 29, 2026, 6:11 p.m.