Triple
T28714363
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Weihsien |
E729916
|
entity |
| Predicate | campPopulationType |
P72572
|
FINISHED |
| Object | civilian internees |
—
|
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: civilian internees | Statement: [Weihsien, campPopulationType, civilian internees]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: campPopulationType Context triple: [Weihsien, campPopulationType, civilian internees]
-
A.
hostedPopulationType
chosen
Indicates the type or category of population that is accommodated or supported by a given host entity.
-
B.
servicePopulationType
Indicates the type or category of population that a service is intended to serve or target.
-
C.
hasPopulationType
Indicates that an entity’s population is classified according to a specific type or category (e.g., demographic, biological, or statistical grouping).
-
D.
staffPopulationApprox
Indicates an approximate or estimated number of staff associated with an entity.
-
E.
hadPopulationType
Indicates that an entity possessed a particular classification or type of population during a given time or context.
- 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_69f043e7d5a4819094b18aca10b1e024 |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69f656d9e6e0819083d05615ec846b1d |
completed | May 2, 2026, 7:56 p.m. |
| PD | Predicate disambiguation | batch_69f651ac855481908e30c3b345d31356 |
completed | May 2, 2026, 7:34 p.m. |
Created at: April 28, 2026, 5:50 a.m.