Triple
T21286042
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chang Chun-hsiung |
E524660
|
entity |
| Predicate | servedAsPremier |
P66236
|
FINISHED |
| Object | twice |
—
|
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: twice | Statement: [Chang Chun-hsiung, servedAsPremier, twice]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servedAsPremier Context triple: [Chang Chun-hsiung, servedAsPremier, twice]
-
A.
servedAsFirstMinisterWith
Indicates that a person held the position of First Minister in association with a specified government, administration, or jurisdiction.
-
B.
servedUnderPrimeMinister
Indicates that one person held a governmental or official position subordinate to, and during the tenure of, a particular prime minister.
-
C.
heldOfficeOfPrimeMinisterThrough
Indicates that an entity continuously occupied and exercised the role and responsibilities of Prime Minister throughout a specified time period.
-
D.
officeHeldAsPrimeMinister
chosen
Indicates that an individual holds or has held the specific office or position of Prime Minister.
-
E.
assumedOfficeAsPremier
Indicates that an individual formally took up and began serving in the role of premier.
- 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_69e0b5171f6c8190a5d57201ede73811 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e736d658e08190ad2f267123d53ede |
completed | April 21, 2026, 8:35 a.m. |
| PD | Predicate disambiguation | batch_69e61612ab748190a72b8703b938abcb |
completed | April 20, 2026, 12:03 p.m. |
Created at: April 16, 2026, 4:03 p.m.