Triple
T38183728
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Iwakuni |
E1005245
|
entity |
| Predicate | formerDomainCenter |
P201752
|
FINISHED |
| Object | Iwakuni Domain |
—
|
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: Iwakuni Domain | Statement: [Iwakuni, formerDomainCenter, Iwakuni Domain]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerDomainCenter Context triple: [Iwakuni, formerDomainCenter, Iwakuni Domain]
-
A.
laterDomainCenter
Indicates that one domain center occurs at a later time or stage than another domain center within a given context.
-
B.
formerDomain
Indicates that one entity was previously the domain or area of control, influence, or ownership of another entity, but no longer is.
-
C.
domainCenter
Indicates that something is located at or serves as the central point or core area of a specified domain or region.
-
D.
formerAdminCenter
chosen
Indicates that an entity once served as an administrative center for another entity but no longer holds that status.
-
E.
publicDomain
Indicates that a work or resource is not protected by intellectual property rights and is freely available for anyone to use, copy, modify, and distribute without restriction.
- 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_69f76dbc22c481908139b694ffde7a0c |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a013a251b4081908b43d85dd95586c5 |
completed | May 11, 2026, 2:08 a.m. |
| PD | Predicate disambiguation | batch_6a0137e4ea988190812173a5ff044098 |
completed | May 11, 2026, 1:59 a.m. |
Created at: May 3, 2026, 4:29 p.m.