Triple
T3285368
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | the Faun |
E68966
|
entity |
| Predicate | claimsIdentityOf |
P16616
|
FINISHED |
| Object | servant of the underworld king |
—
|
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: servant of the underworld king | Statement: [the Faun, claimsIdentityOf, servant of the underworld king]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: claimsIdentityOf Context triple: [the Faun, claimsIdentityOf, servant of the underworld king]
-
A.
attributeClaim
chosen
Indicates that one entity asserts or specifies a particular attribute or property about another entity.
-
B.
subjectIdentity
Indicates that two or more references correspond to the same underlying entity or individual identity.
-
C.
identityConcept
Indicates that two concepts are the same in identity, representing exactly the same underlying idea or meaning.
-
D.
identityComponent
Indicates that one entity functions as an identifying or defining part of another entity, contributing to its overall identity.
-
E.
identityRevealedIn
Indicates that an entity’s true identity becomes known or disclosed within a specified context, source, or situation.
- 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_69ad859c463481909ca4be267336c290 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb03918c48190987d7cfd3bda9716 |
completed | March 8, 2026, 5:22 p.m. |
| PD | Predicate disambiguation | batch_69ada421fadc8190b7c7d3c8afd20061 |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:10 p.m.