Triple
T27979705
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2016 Conservative Party leadership election |
E706584
|
entity |
| Predicate | finalBallotCandidates |
P126858
|
FINISHED |
| Object | Theresa May |
—
|
NE NERFINISHED |
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: Theresa May | Statement: [2016 Conservative Party leadership election, finalBallotCandidates, Theresa May]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: finalBallotCandidates Context triple: [2016 Conservative Party leadership election, finalBallotCandidates, Theresa May]
-
A.
finalBallotCandidate
chosen
Indicates that an entity is a candidate who appears on the final ballot in an election or selection process.
-
B.
firstBallotCandidate
Indicates that the entity was a candidate in the first ballot of an election or selection process.
-
C.
leadingCandidateEarlyBallots
Indicates that a candidate is currently leading in vote counts based solely on early ballots cast before the main election day.
-
D.
ballotsInclude
Indicates that a given set of ballots contains or records the specified option, candidate, or choice.
-
E.
nominatedOnBallot
Indicates that an entity has been officially proposed or listed as a candidate on a specific ballot for selection or voting.
- F. None of above.
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_69ef96b7f330819090f315318ba6977e |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69f7764ab1fc81909f9348db87bd7692 |
completed | May 3, 2026, 4:22 p.m. |
| PD | Predicate disambiguation | batch_69f76905d9c88190b1ee810bc9ab644f |
completed | May 3, 2026, 3:25 p.m. |
Created at: April 27, 2026, 7:43 p.m.