Triple
T28283823
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prince of Duan |
E713224
|
entity |
| Predicate | associatedTitleHolderTempleName |
P129565
|
FINISHED |
| Object | Huizong |
—
|
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: Huizong | Statement: [Prince of Duan, associatedTitleHolderTempleName, Huizong]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedTitleHolderTempleName Context triple: [Prince of Duan, associatedTitleHolderTempleName, Huizong]
-
A.
templeTitleOf
chosen
Indicates that one entity is the formal religious or ceremonial title held by another entity within a temple or sacred context.
-
B.
templeName
Indicates that an entity is identified by or associated with the name of a temple.
-
C.
associatedWithTempleName
Indicates a relationship where an entity is linked or connected to a specific temple by its name.
-
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.
linkedRulerTempleName
Indicates that a specific ruler is associated with, or has a named connection to, a particular temple.
- 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_69efb52371d88190a1381c4e58a3b731 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_6a011ee3507081908b42de4278ae0b83 |
completed | May 11, 2026, 12:12 a.m. |
| PD | Predicate disambiguation | batch_6a011e874420819091cac3f08e8aa3f9 |
completed | May 11, 2026, 12:10 a.m. |
Created at: April 27, 2026, 11:24 p.m.