Triple
T23292419
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sai-in (Western Precinct) |
E590066
|
entity |
| Predicate | isWesternPrecinctOf |
P117385
|
FINISHED |
| Object | Hōryū-ji |
—
|
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: Hōryū-ji | Statement: [Sai-in (Western Precinct), isWesternPrecinctOf, Hōryū-ji]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isWesternPrecinctOf Context triple: [Sai-in (Western Precinct), isWesternPrecinctOf, Hōryū-ji]
-
A.
partOfPrecinct
chosen
Indicates that one entity is a subdivision or component contained within a specific precinct.
-
B.
isMajorPrecinctFor
Indicates that one entity serves as the primary or main precinct responsible for another entity within a given jurisdiction or context.
-
C.
hasInnerPrecinct
Indicates that one area, structure, or zone contains another, more central or enclosed precinct within its boundaries.
-
D.
hasNumberedPrecinct
Indicates that an entity is associated with a specific precinct identified by a number.
-
E.
hasNearbyPrecinct
Indicates that one location has a police precinct or similar administrative station situated close to it in geographic proximity.
- 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_69e25d1af9d88190a0b9b5e8fa608618 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f196cc20c08190a6a678befe1061dd |
completed | April 29, 2026, 5:27 a.m. |
| PD | Predicate disambiguation | batch_69effcf325f88190b320268c3c551abb |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 5:02 p.m.