Triple
T35454769
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Danielle Dyce |
E1024739
|
entity |
| Predicate | operatesUnderAlias |
P160425
|
FINISHED |
| Object | Red Raven |
—
|
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: Red Raven | Statement: [Danielle Dyce, operatesUnderAlias, Red Raven]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatesUnderAlias Context triple: [Danielle Dyce, operatesUnderAlias, Red Raven]
-
A.
operatesUnderName
Indicates that an entity conducts its activities or business using a particular name, which may differ from its official or legal name.
-
B.
assumesAlias
chosen
Indicates that one entity adopts, uses, or operates under an alternative name or identity associated with another entity.
-
C.
usesAliasOnline
Indicates that an entity operates or interacts online under an alternative name or pseudonymous identifier instead of their primary or real identity.
-
D.
usesAliasFor
Indicates that one entity employs an alternative name or identifier to refer to another entity.
-
E.
hasOccupationUnderAlias
Indicates that an entity holds or held a particular occupation while using a specific alias or alternate name.
- 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_69f76df92f108190817222e520e22268 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a01416f8a8c8190abc12f68bd23dcc3 |
completed | May 11, 2026, 2:39 a.m. |
| PD | Predicate disambiguation | batch_6a013f3bc2e48190a51ec2707bbdd474 |
completed | May 11, 2026, 2:30 a.m. |
Created at: May 3, 2026, 4:04 p.m.