Triple
T26081393
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New Hampshire Democratic primary 2000 |
E657853
|
entity |
| Predicate | campaignRivals |
P148634
|
FINISHED |
| Object | Bill Bradley |
—
|
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: Bill Bradley | Statement: [New Hampshire Democratic primary 2000, campaignRivals, Bill Bradley]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: campaignRivals Context triple: [New Hampshire Democratic primary 2000, campaignRivals, Bill Bradley]
-
A.
campaignOpponents
Indicates that two entities are on opposing sides in a political or advocacy campaign.
-
B.
rivalOf
Indicates a relationship in which two entities compete against or oppose each other, often seeking advantage in the same domain or objective.
-
C.
campaignOpponent
chosen
Indicates that one entity is an opponent or rival of another in a political or similar competitive campaign.
-
D.
competitionFrom
Indicates that one entity is experiencing competitive pressure or rivalry originating from another entity.
-
E.
opponentCampaign
Indicates a relationship where one campaign is positioned as competing against or opposing another campaign.
- 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_69ee5bbf0d208190801ee95d4f07fb16 |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69f60c698ae48190871cd445422bad91 |
completed | May 2, 2026, 2:38 p.m. |
| PD | Predicate disambiguation | batch_69f60b874cc88190a487230abb69efea |
completed | May 2, 2026, 2:34 p.m. |
Created at: April 26, 2026, 7:38 p.m.