Triple
T33752007
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zhou Cang |
E864866
|
entity |
| Predicate | in-universeAffiliation |
P120153
|
FINISHED |
| Object | Guan Yu’s personal retinue |
—
|
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: Guan Yu’s personal retinue | Statement: [Zhou Cang, in-universeAffiliation, Guan Yu’s personal retinue]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: in-universeAffiliation Context triple: [Zhou Cang, in-universeAffiliation, Guan Yu’s personal retinue]
-
A.
notableCharacterAffiliation
chosen
Indicates that a notable character is formally associated with, aligned to, or a member of a particular group, organization, or affiliation.
-
B.
inUniverseAffiliationType
Indicates the type or category of affiliation an entity has within a particular fictional or narrative universe.
-
C.
characterAffiliationPortrayed
Indicates that a portrayal shows a character as being affiliated with a particular group, organization, or side.
-
D.
commanderAffiliation
Indicates that a commander is formally associated with, belongs to, or serves under a particular organization, group, or side.
-
E.
playerCharacterAffiliation
Indicates the group, faction, or organization with which a player-controlled character is associated or aligned.
- 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_69f3498c35f881909df279ae4270f831 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6fb8ffae48190a4244047eab033e4 |
completed | May 3, 2026, 7:38 a.m. |
| PD | Predicate disambiguation | batch_69f6f96ea0c08190902a3d0e1f263e8c |
completed | May 3, 2026, 7:29 a.m. |
Created at: May 1, 2026, 1:45 a.m.