Triple
T29917469
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 中元節 |
E759825
|
entity |
| Predicate | 所屬宗教傳統 |
P23614
|
FINISHED |
| Object | 道教 |
—
|
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: 道教 | Statement: [中元節, 所屬宗教傳統, 道教]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 所屬宗教傳統 Context triple: [中元節, 所屬宗教傳統, 道教]
-
A.
partOfReligiousTradition
chosen
Indicates that one entity belongs to, is included within, or is practiced as a component of a particular religious tradition.
-
B.
religiousTraditions
Indicates a relationship where certain religious customs, practices, or belief systems are associated with or observed by an entity.
-
C.
theologicalTradition
Indicates the religious or doctrinal school, lineage, or system of belief within which an entity’s theology is developed or practiced.
-
D.
religiousTraditionDetail
Indicates the specific religious tradition, denomination, or doctrinal detail associated with an entity or relationship.
-
E.
religionAccordingToTradition
Indicates that an entity’s religion is identified or classified according to a particular tradition or customary understanding, rather than strictly formal or official criteria.
- 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_69f2246189fc8190996b63ee1f9a2374 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f677907930819081cd718537fdaf4a |
completed | May 2, 2026, 10:15 p.m. |
| PD | Predicate disambiguation | batch_69f66ec8298c8190b41fe9d182c05676 |
completed | May 2, 2026, 9:38 p.m. |
Created at: April 29, 2026, 6:13 p.m.