Triple
T33941387
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bunji |
E870173
|
entity |
| Predicate | eraSequencePosition |
P110498
|
FINISHED |
| Object | after Genryaku and before Kenkyū |
—
|
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: after Genryaku and before Kenkyū | Statement: [Bunji, eraSequencePosition, after Genryaku and before Kenkyū]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eraSequencePosition Context triple: [Bunji, eraSequencePosition, after Genryaku and before Kenkyū]
-
A.
eraSequence
chosen
Indicates that one era or time period directly follows or precedes another in a chronological sequence.
-
B.
hasSequencePosition
Indicates that an element occupies a specific position or order within a sequence.
-
C.
eraStartLocation
Indicates the place where a particular era or time period begins or is initiated.
-
D.
segmentPosition
Indicates the relative location or ordering of a segment within a larger sequence or structure.
-
E.
segmentPositioning
Indicates how segments are arranged or ordered relative to one another within a larger structure or sequence.
- 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_69f3499b0dd48190b07b4b60babcee02 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7064e906881909c3186c646145d34 |
completed | May 3, 2026, 8:24 a.m. |
| PD | Predicate disambiguation | batch_69f70100ec1c8190a6b97f50e88891f2 |
completed | May 3, 2026, 8:02 a.m. |
Created at: May 1, 2026, 1:49 a.m.