Triple
T16085497
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Indiana gubernatorial election |
E390218
|
entity |
| Predicate | positionHeldByWinner |
P8
|
FINISHED |
| Object | Governor of Indiana |
—
|
LITERAL 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: Governor of Indiana | Statement: [Indiana gubernatorial election, positionHeldByWinner, Governor of Indiana]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionHeldByWinner Context triple: [Indiana gubernatorial election, positionHeldByWinner, Governor of Indiana]
-
A.
positionHeld
chosen
Indicates that an entity occupies or has occupied a specific role, job, office, or position within an organization or context.
-
B.
positionOfWinner
Indicates the relationship that identifies which entity holds the winning position or rank in a competition or contest.
-
C.
finalHeld
Indicates that an entity ultimately retains possession or control of another entity at the conclusion of a process or event.
-
D.
lastWinner
Indicates that one entity is the most recent winner in a sequence of competitions, contests, or events involving the other entity.
-
E.
speakerSeatsWon
Indicates the number of seats won by the entity serving or designated as the speaker in a given election or legislative context.
- 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_69d87f198bc48190a8b7e53ca15b7ead |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e1ff63edb0819092cbb671967bbdcd |
completed | April 17, 2026, 9:37 a.m. |
| PD | Predicate disambiguation | batch_69e1827ad7c88190b867da511cbfb7fa |
completed | April 17, 2026, 12:44 a.m. |
Created at: April 10, 2026, 4:59 a.m.