Triple
T4117454
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Republican Party presidential primaries, 2008 |
E90326
|
entity |
| Predicate | totalDelegates |
P10538
|
FINISHED |
| Object | 2380 |
—
|
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: 2380 | Statement: [Republican Party presidential primaries, 2008, totalDelegates, 2380]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: totalDelegates Context triple: [Republican Party presidential primaries, 2008, totalDelegates, 2380]
-
A.
numberOfDelegates
chosen
Indicates the quantity of delegates associated with or assigned to a particular entity or event.
-
B.
nonVotingDelegatesCount
Indicates the number of delegates associated with an entity who do not possess voting rights in a given decision-making process.
-
C.
delegates
Indicates that one entity assigns or entrusts a task, responsibility, or authority to another entity to act on its behalf.
-
D.
electsDelegatesTo
Indicates that one entity selects or votes to choose representatives (delegates) who will act or decide on its behalf in another body or process.
-
E.
delegateCountWinner
Indicates that the referenced entity is the candidate or option that has secured the highest number of delegates in a given selection or election process.
- 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_69aed95c080881908125e30c5dcdc6f8 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af0246e40081908ad6741a830ca68e |
completed | March 9, 2026, 5:24 p.m. |
| PD | Predicate disambiguation | batch_69af01867698819098e4144634b2ec4f |
completed | March 9, 2026, 5:21 p.m. |
Created at: March 9, 2026, 3:41 p.m.