Triple
T20566631
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kong Ji |
E504980
|
entity |
| Predicate | inConfucianGenealogy |
P77019
|
FINISHED |
| Object | disciple in the lineage of Confucius |
—
|
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: disciple in the lineage of Confucius | Statement: [Kong Ji, inConfucianGenealogy, disciple in the lineage of Confucius]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inConfucianGenealogy Context triple: [Kong Ji, inConfucianGenealogy, disciple in the lineage of Confucius]
-
A.
genealogicalFunction
Indicates a genealogical relationship or role that one entity holds in relation to another within a family or ancestry structure.
-
B.
genealogicalClassification
chosen
Indicates a relationship where one entity is categorized within a family or lineage structure relative to another, based on genealogical or ancestral connections.
-
C.
oldChineseReconstruction
Indicates that something represents a reconstructed form or pronunciation in Old Chinese.
-
D.
formedDynasty
Indicates that an entity established or created a ruling dynasty.
-
E.
hasGenealogicalSignificance
Indicates that something holds importance or relevance within a genealogical or family-lineage context.
- 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_69e0b4b6587c8190aee63dc7cff244ea |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6a7a33f7c8190966da03528dfe8aa |
completed | April 20, 2026, 10:24 p.m. |
| PD | Predicate disambiguation | batch_69e59ff0116c8190a163ff28ed01430a |
completed | April 20, 2026, 3:39 a.m. |
Created at: April 16, 2026, 11:39 a.m.