Triple
T23665614
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Xuanzang |
E584569
|
entity |
| Predicate | mainAffiliation |
P45107
|
FINISHED |
| Object | Tang dynasty |
—
|
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 dynasty | Statement: [Xuanzang, mainAffiliation, Tang dynasty]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainAffiliation Context triple: [Xuanzang, mainAffiliation, Tang dynasty]
-
A.
primaryAffiliation
chosen
Indicates the main organization, institution, or group with which an entity is chiefly associated or formally connected.
-
B.
modernAffiliation
Indicates a current or contemporary organizational, institutional, or group association between entities, as opposed to a historical or past affiliation.
-
C.
administrativeAffiliation
Indicates that one entity is formally connected to, governed by, or overseen by another entity within an administrative or organizational structure.
-
D.
holderAffiliation
Indicates that a holder (such as a person or organization) is affiliated with, or belongs to, a particular group, institution, or entity.
-
E.
commonAffiliation
Indicates that two or more entities share the same organizational, institutional, or group affiliation.
- 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_69e24901421881908c17a5293bdd4a8e |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b40b8bd48190922c7252e71a5421 |
completed | April 29, 2026, 7:32 a.m. |
| PD | Predicate disambiguation | batch_69f118dd13008190a8799b4e9cadbd79 |
completed | April 28, 2026, 8:30 p.m. |
Created at: April 17, 2026, 6:50 p.m.