Triple
T27960182
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kaiyuan era |
E704556
|
entity |
| Predicate | usedByTempleName |
P118620
|
FINISHED |
| Object | Tang Xuanzong |
—
|
NE NERFINISHED |
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: Tang Xuanzong | Statement: [Kaiyuan era, usedByTempleName, Tang Xuanzong]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedByTempleName Context triple: [Kaiyuan era, usedByTempleName, Tang Xuanzong]
-
A.
templeNameUsage
chosen
Indicates how a temple’s name is used or referenced in relation to other entities or contexts.
-
B.
templeName
Indicates that an entity is identified by or associated with the name of a temple.
-
C.
templeUse
Indicates that something is used as, functions as, or serves the purpose of a temple.
-
D.
associatedTemple
Indicates a relationship where one entity is linked or connected to a particular temple, typically as its relevant or related religious site.
-
E.
attributesTempleTo
Indicates that a particular temple is ascribed, assigned, or associated to a specific entity, such as a deity, person, group, or place.
- 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_69ef841061e48190b5570f9562f7434d |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_69f6cee45590819086e489bfccbe4ac3 |
completed | May 3, 2026, 4:28 a.m. |
| PD | Predicate disambiguation | batch_69f6cc1188708190b8f0f56e595e6057 |
completed | May 3, 2026, 4:16 a.m. |
Created at: April 27, 2026, 7:31 p.m.