Triple
T26286294
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bill Bradley 2000 presidential campaign |
E661147
|
entity |
| Predicate | keyEndorser |
P37962
|
FINISHED |
| Object | Patrick Moynihan |
—
|
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: Patrick Moynihan | Statement: [Bill Bradley 2000 presidential campaign, keyEndorser, Patrick Moynihan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: keyEndorser Context triple: [Bill Bradley 2000 presidential campaign, keyEndorser, Patrick Moynihan]
-
A.
primaryEndorser
Indicates that an entity serves as the main or principal supporter, recommender, or approver of another entity or action.
-
B.
hasEndorser
chosen
Indicates that one entity supports, approves, or publicly backs another entity, typically lending it credibility or validation.
-
C.
keyProponent
Indicates that the subject is a primary supporter, advocate, or driving force behind the object.
-
D.
keyIdentifier
Indicates that one entity serves as a unique key or identifying code used to distinguish or reference another entity.
-
E.
keyClient
Indicates that one entity is a primary or strategically important client of another entity.
- 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_69ee812bbd448190be4d7478b057990a |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f60e77611081908d8719871d42015a |
completed | May 2, 2026, 2:47 p.m. |
| PD | Predicate disambiguation | batch_69f602d2ec748190ae95154f34c7878f |
completed | May 2, 2026, 1:57 p.m. |
Created at: April 26, 2026, 10:04 p.m.