Triple
T9007912
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sendai Castle ruins |
E215390
|
entity |
| Predicate | hasInformationBoards |
P51898
|
FINISHED |
| Object | historical explanations |
—
|
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: historical explanations | Statement: [Sendai Castle ruins, hasInformationBoards, historical explanations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasInformationBoards Context triple: [Sendai Castle ruins, hasInformationBoards, historical explanations]
-
A.
hasServiceBoard
Indicates that an entity is associated with or connected to a specific service board, such as a panel or group responsible for providing or overseeing services.
-
B.
hasLocalBoards
Indicates that an entity is associated with one or more governing or administrative boards operating at a local or regional level.
-
C.
hasTouristSignage
chosen
Indicates that there is official signage present to guide or inform tourists about a place, route, or attraction.
-
D.
hasSignageIn
Indicates that appropriate signs or signage for an entity are present or installed within a specified location or area.
-
E.
hasInformationCentre
Indicates that one entity possesses, hosts, or is served by an information centre associated with it.
- 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_69ca83a2bf088190986ee7a8eb90407d |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc69bdc5fc819081015f4adacf9fd4 |
completed | April 1, 2026, 12:41 a.m. |
| PD | Predicate disambiguation | batch_69cc5edf84408190aa5f57cb8bfd00e1 |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 7:05 p.m.