Triple
T24333711
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hagi Castle |
E613318
|
entity |
| Predicate | formerRulerRelocatedFrom |
P48071
|
FINISHED |
| Object | Hiroshima Castle |
—
|
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: Hiroshima Castle | Statement: [Hagi Castle, formerRulerRelocatedFrom, Hiroshima Castle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerRulerRelocatedFrom Context triple: [Hagi Castle, formerRulerRelocatedFrom, Hiroshima Castle]
-
A.
formerRulerState
Indicates that an entity previously held ruling authority over a given state or territory but no longer does so.
-
B.
relocatedFrom
Indicates that an entity has moved or been transferred away from a specified original location.
-
C.
hasFormerRuler
Indicates that an entity previously served as the ruler of another entity but no longer holds that ruling position.
-
D.
formerSovereign
Indicates that an entity once held sovereign (ruling) authority over another entity but no longer does.
-
E.
administrativeCenterMovedFrom
chosen
Indicates that the role of administrative center was previously located in one place and has been transferred or relocated from that original location to another.
- 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_69e2d7dcc5a08190b53691130d56cbc4 |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f292f381b08190b529a765a5d5e89b |
completed | April 29, 2026, 11:23 p.m. |
| PD | Predicate disambiguation | batch_69f287ad30048190b3ad3613486f277f |
completed | April 29, 2026, 10:35 p.m. |
Created at: April 18, 2026, 1:56 a.m.