Triple
T25089505
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chiang Kai-shek statues |
E628414
|
entity |
| Predicate | previousTypicalLocation |
P164972
|
FINISHED |
| Object | school campuses in Taiwan |
—
|
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: school campuses in Taiwan | Statement: [Chiang Kai-shek statues, previousTypicalLocation, school campuses in Taiwan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousTypicalLocation Context triple: [Chiang Kai-shek statues, previousTypicalLocation, school campuses in Taiwan]
-
A.
previousLocationName
Indicates that one entity specifies the name of a location where another entity was situated or occurred before its current location.
-
B.
previousLocationInCity
Indicates that an entity was formerly located at a specified place within a particular city before moving or changing location.
-
C.
previousCity
Indicates that one city was the immediately preceding location visited or lived in before another city.
-
D.
previousTrainingLocation
Indicates the place where an entity received training immediately before the current or referenced training event.
-
E.
typicalUseLocation
Indicates the usual or most common location where an entity is used or operates.
- 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_69e2ff2f58e881908340527bc5d34f07 |
completed | April 18, 2026, 3:49 a.m. |
| NER | Named-entity recognition | batch_69f65705a3048190a3728b695ba2ae65 |
completed | May 2, 2026, 7:56 p.m. |
| PD | Predicate disambiguation | batch_69f651a731508190bb0c8c2462eba224 |
completed | May 2, 2026, 7:33 p.m. |
| PDg | Predicate description generation | batch_69f6562ef4e4819082ce6abd41b74dc5 |
completed | May 2, 2026, 7:53 p.m. |
Created at: April 18, 2026, 6:24 a.m.