Triple
T28329173
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Republican Party presidential primaries, 2020 |
E717490
|
entity |
| Predicate | mainContender |
P86017
|
FINISHED |
| Object | Donald Trump |
—
|
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: Donald Trump | Statement: [Republican Party presidential primaries, 2020, mainContender, Donald Trump]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainContender Context triple: [Republican Party presidential primaries, 2020, mainContender, Donald Trump]
-
A.
mainDebater
Indicates that an entity serves as the primary or lead participant in a debate or argumentative exchange.
-
B.
contestantOn
Indicates that one entity participates as a competitor in a contest, show, or competition associated with another entity.
-
C.
hasNotableContender
Indicates that an entity has a significant rival, challenger, or competitor recognized as noteworthy in relation to it.
-
D.
primaryChallengers
chosen
Indicates that certain entities are the main or most significant opponents or competitors challenging another entity.
-
E.
laterContestedBy
Indicates that an earlier claim, decision, or statement is subsequently challenged or disputed by another party or source.
- 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_69eff6e9a57c8190a69c2c74b5d72119 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f6df450014819099d118e5c2d697fa |
completed | May 3, 2026, 5:38 a.m. |
| PD | Predicate disambiguation | batch_69f6de07836481908785cde9c511920b |
completed | May 3, 2026, 5:32 a.m. |
Created at: April 28, 2026, 12:30 a.m.