Triple
T27823534
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 洪秀柱 |
E702884
|
entity |
| Predicate | predecessorAsKMTChair |
P126793
|
FINISHED |
| Object | 朱立倫 |
—
|
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: 朱立倫 | Statement: [洪秀柱, predecessorAsKMTChair, 朱立倫]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: predecessorAsKMTChair Context triple: [洪秀柱, predecessorAsKMTChair, 朱立倫]
-
A.
predecessorChairpersonModel
chosen
Indicates that one entity served as the chairperson immediately before another entity in a sequence of chairperson roles.
-
B.
precededBy (KMT chairman, 2009)
Indicates that the subject held the position of KMT chairman immediately before the person who was KMT chairman in 2009.
-
C.
precededBy (KMT chairman, 2005)
Indicates that one entity held the position of KMT chairman immediately before the specified 2005 officeholder.
-
D.
predecessorCEO
Indicates that one person previously held the position of CEO before another specific person.
-
E.
predecessorAsTreasurer
Indicates that one entity previously held the role of treasurer before another entity, establishing a predecessor relationship in that office.
- 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_69ef840ad1e88190b5bff2d1ddec8700 |
completed | April 27, 2026, 3:43 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 27, 2026, 5:50 p.m.