Triple
T18238501
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 归元禅寺 |
E436743
|
entity |
| Predicate | 相关宗教人物 |
P57866
|
FINISHED |
| Object | 僧人 |
—
|
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: 僧人 | Statement: [归元禅寺, 相关宗教人物, 僧人]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 相关宗教人物 Context triple: [归元禅寺, 相关宗教人物, 僧人]
-
A.
religiousFigure
Indicates that one entity is recognized or designated as a religious leader, authority, or sacred person in relation to another entity.
-
B.
hasReligiousFigureAssociation
chosen
Indicates a relationship in which an entity is connected or linked to a religious figure, such as through dedication, representation, influence, or affiliation.
-
C.
religiousFigureType
Indicates the specific role or category of a person recognized as a religious figure (e.g., priest, monk, prophet) within a religious context.
-
D.
hasReligiousCharacter
Indicates that an entity possesses a religious nature, function, or affiliation, or is characterized by religious aspects or significance.
-
E.
commemoratedPersonReligion
Indicates the religious affiliation or belief system of the person who is being commemorated.
- 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_69d8b91104e08190a8241f7d260a5162 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4f7e0a0ac819090d48ae45b1ebfc9 |
completed | April 19, 2026, 3:42 p.m. |
| PD | Predicate disambiguation | batch_69e4332336cc8190808b9c70c888ba65 |
completed | April 19, 2026, 1:42 a.m. |
Created at: April 10, 2026, 10:33 a.m.