Triple
T27489773
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2000 Taiwanese presidential election |
E693845
|
entity |
| Predicate | panBlueCandidate |
P162666
|
FINISHED |
| Object | James Soong |
—
|
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: James Soong | Statement: [2000 Taiwanese presidential election, panBlueCandidate, James Soong]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: panBlueCandidate Context triple: [2000 Taiwanese presidential election, panBlueCandidate, James Soong]
-
A.
panGreenCandidate
Indicates that an individual is a political candidate affiliated with the Pan-Green coalition.
-
B.
mainGovernmentCandidate
Indicates that the subject is the primary or officially designated candidate for a government position, office, or role.
-
C.
nominatedCandidateOfParty
Indicates that a specific candidate has been officially selected or endorsed by a particular political party as its nominee.
-
D.
generalElectionCandidate
Indicates that a person is a candidate running for office in a general election.
-
E.
democraticNominationContender
Indicates that an entity is a candidate actively competing for the Democratic Party’s nomination for a particular political office.
- F. None of above. chosen
Provenance (4 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_69ef5382b9648190be0b1ef2ad5d043c |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f62e882cbc81908caa3e8a5fb5c1f4 |
completed | May 2, 2026, 5:04 p.m. |
| PD | Predicate disambiguation | batch_69f62c1762f881908c25e8f70ecd5041 |
completed | May 2, 2026, 4:53 p.m. |
| PDg | Predicate description generation | batch_69f62cd1912c8190ab3f3288442115a4 |
completed | May 2, 2026, 4:56 p.m. |
Created at: April 27, 2026, 1:04 p.m.