Triple
T28921197
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lily Savage’s Blankety Blank |
E733515
|
entity |
| Predicate | presenterAlterEgoOf |
P86336
|
FINISHED |
| Object | Paul O’Grady |
—
|
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: Paul O’Grady | Statement: [Lily Savage’s Blankety Blank, presenterAlterEgoOf, Paul O’Grady]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: presenterAlterEgoOf Context triple: [Lily Savage’s Blankety Blank, presenterAlterEgoOf, Paul O’Grady]
-
A.
presenterOccupation
Indicates that an entity serves in a specific professional role or job as a presenter.
-
B.
hasFictionalAlterEgoOf
chosen
Indicates that one entity is the fictional alter ego, persona, or alternate identity of another entity.
-
C.
presenterAbbreviation
Indicates that one entity is an abbreviation or shortened form used to refer to a presenter in the context of a presentation or event.
-
D.
presenterField
Indicates that an entity serves as the presenter or speaker associated with a particular field, session, or content item.
-
E.
protagonistAlterEgoOf
Indicates that one entity is the alternate identity or secret persona of the main character (protagonist) in a narrative.
- 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_69f05b0a5cc0819094828367ae204b70 |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69f73ae120bc8190bff94d38d7a7a00d |
completed | May 3, 2026, 12:09 p.m. |
| PD | Predicate disambiguation | batch_69f73a38d0848190aa5139144b8561c6 |
completed | May 3, 2026, 12:06 p.m. |
Created at: April 28, 2026, 8:19 a.m.