Triple
T32385166
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ban Liang |
E827527
|
entity |
| Predicate | writingOnObverse |
P23868
|
FINISHED |
| Object | characters 'Ban' and 'Liang' |
—
|
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: characters 'Ban' and 'Liang' | Statement: [Ban Liang, writingOnObverse, characters 'Ban' and 'Liang']
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: writingOnObverse Context triple: [Ban Liang, writingOnObverse, characters 'Ban' and 'Liang']
-
A.
obverseText
chosen
Indicates the text that appears on the front (obverse) side of an object, typically a coin or medal.
-
B.
writtenInside
Indicates that one entity is physically inscribed or written within the boundaries or interior of another entity.
-
C.
areWrittenOn
Indicates that one entity serves as a surface or medium on which another entity is inscribed, recorded, or written.
-
D.
wroteIn
Indicates that an entity authored or composed something using a particular language, medium, or writing system.
-
E.
willWrittenIn
Indicates that a legal will was authored, drafted, or formally written in a specified location or jurisdiction.
- 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_69f349184e7481909c6c54428cb9cf12 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6c1cf2aa081909f4c0b8f0cad1907 |
completed | May 3, 2026, 3:32 a.m. |
| PD | Predicate disambiguation | batch_69f6ba6eb32c8190bf405b2011fa48f7 |
completed | May 3, 2026, 3:01 a.m. |
Created at: May 1, 2026, 12:51 a.m.