Triple
T23759243
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dongyue Emperor |
E587203
|
entity |
| Predicate | worshipperConcern |
P134244
|
FINISHED |
| Object | longevity |
—
|
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: longevity | Statement: [Dongyue Emperor, worshipperConcern, longevity]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: worshipperConcern Context triple: [Dongyue Emperor, worshipperConcern, longevity]
-
A.
worshipIssue
chosen
Indicates that one entity has a concern, problem, or topic specifically related to worship in relation to another entity.
-
B.
worshipperType
Indicates the specific category or kind of worshipper involved in a religious or devotional relationship or action.
-
C.
worshipperCommunity
Indicates that one entity is a community or group of people who collectively worship or devote religious reverence to another entity.
-
D.
worship
Indicates a relationship where one entity shows reverence, adoration, or religious devotion toward another entity, often recognizing it as sacred or divine.
-
E.
worshipLevel
Indicates the degree or intensity to which one entity reveres, honors, or performs acts of worship toward another entity.
- 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_69e2490a0eec81908cdef8a862828d7a |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1bdaf52848190b034208de4c4e01a |
completed | April 29, 2026, 8:13 a.m. |
| PD | Predicate disambiguation | batch_69f155f79e34819080f9ddb972b34deb |
completed | April 29, 2026, 12:51 a.m. |
Created at: April 17, 2026, 7:14 p.m.