Triple
T6903564
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yata no Kagami |
E159550
|
entity |
| Predicate | componentOfSet |
P69124
|
FINISHED |
| Object | mirror, sword, and jewel |
—
|
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: mirror, sword, and jewel | Statement: [Yata no Kagami, componentOfSet, mirror, sword, and jewel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: componentOfSet Context triple: [Yata no Kagami, componentOfSet, mirror, sword, and jewel]
-
A.
isAComponentOf
chosen
Indicates that one entity functions as a constituent part or sub-unit of another, larger entity.
-
B.
setsIn
Indicates that one entity places or positions another entity into or within a specified container, location, or context.
-
C.
sets
Indicates that an entity places, positions, or puts another entity into a particular state, location, or configuration.
-
D.
isCoreComponentOf
Indicates that something is an essential, foundational part required for the structure, function, or identity of another entity.
-
E.
set
Indicates that an entity places, positions, or establishes another entity into a particular state, configuration, or location.
- 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_69c6883822e0819091e321526f20ae0a |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6d988a5b48190a9238047e86f314c |
completed | March 27, 2026, 7:24 p.m. |
| PD | Predicate disambiguation | batch_69c6d7b7681481909ec50509b19fcf81 |
completed | March 27, 2026, 7:17 p.m. |
Created at: March 27, 2026, 2:25 p.m.