Triple
T2089260
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taihoku |
E32628
|
entity |
| Predicate | colonialRole |
P16892
|
FINISHED |
| Object | seat of the Governor-General of 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: seat of the Governor-General of Taiwan | Statement: [Taihoku, colonialRole, seat of the Governor-General of Taiwan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: colonialRole Context triple: [Taihoku, colonialRole, seat of the Governor-General of Taiwan]
-
A.
roleInColonies
chosen
Indicates the specific function, position, or responsibility an entity holds within one or more colonies.
-
B.
colonialOffshoot
Indicates that one entity originated as a colony or derivative settlement established by another entity.
-
C.
colonialPowerInvolved
Indicates that a colonial power is involved in, influences, or exerts control over the referenced situation, event, or relationship.
-
D.
colonialLegacy
Indicates the enduring influence or consequences of a past colonial relationship that continue to shape interactions or conditions between entities.
-
E.
usedInColonialAdministration
Indicates that something was employed as a tool, system, or resource within the structures or practices of colonial governance and administration.
- 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_69a885eba0708190999696a45cbec816 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69abba730a5c8190a85be72149574d79 |
completed | March 7, 2026, 5:41 a.m. |
| PD | Predicate disambiguation | batch_69abb7b4356881909217c42ccb8bb1ed |
completed | March 7, 2026, 5:29 a.m. |
Created at: March 4, 2026, 7:43 p.m.