Triple
T38587183
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cathedral of Light |
E932370
|
entity |
| Predicate | associatedWithNPCType |
P47706
|
FINISHED |
| Object | priests |
—
|
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: priests | Statement: [Cathedral of Light, associatedWithNPCType, priests]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedWithNPCType Context triple: [Cathedral of Light, associatedWithNPCType, priests]
-
A.
associatedWithCharacterGroup
chosen
Indicates that an entity has a connection or affiliation with a particular group of characters.
-
B.
associatedWithMagicType
Indicates a relationship where something is linked or connected to a particular type or category of magic.
-
C.
associatedWithMonster
Indicates a relationship in which an entity is connected or linked in some notable way to a monster.
-
D.
associatedWithCharacterRole
Indicates that one entity has a connection or linkage to a specific character role played or held by another entity.
-
E.
associatedWithFilmCharacterType
Indicates that an entity has an association or connection with a particular type or category of film character.
- 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_69f76ec654d48190b421111cf26e54d9 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c903be48190a2fafa53d7d50d42 |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a1e32108190897356d6a7fed879 |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:32 p.m.