Triple
T28369600
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oshima District, Kagoshima |
E718588
|
entity |
| Predicate | hasFormerTown |
P54403
|
FINISHED |
| Object | Kasari, Kagoshima |
—
|
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: Kasari, Kagoshima | Statement: [Oshima District, Kagoshima, hasFormerTown, Kasari, Kagoshima]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFormerTown Context triple: [Oshima District, Kagoshima, hasFormerTown, Kasari, Kagoshima]
-
A.
cityPreviouslyLocatedIn
Indicates that a city was formerly situated within a specified location or administrative region, but is no longer located there.
-
B.
hasFormerSettlement
chosen
Indicates that a location previously contained a settlement that no longer exists or is no longer inhabited.
-
C.
hasOldCity
Indicates that an entity possesses or contains an old or historic city as part of its domain or structure.
-
D.
hasNearbyFormerResidenceOf
Indicates that one entity is located near a place that used to be the residence of another entity.
-
E.
formerResidenceOf
Indicates that a location was once the place where a person or entity lived or was based, but is no longer their current residence.
- 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_69eff6ed5af48190be4e0adf298223e0 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f75dc25fa08190b371faf36d9fb72c |
completed | May 3, 2026, 2:37 p.m. |
| PD | Predicate disambiguation | batch_69f758586534819083e91172f4bf5098 |
completed | May 3, 2026, 2:14 p.m. |
Created at: April 28, 2026, 12:58 a.m.