Triple
T26640411
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leslie Glass |
E668765
|
entity |
| Predicate | fictionalDetectiveCreated |
P63938
|
FINISHED |
| Object | April Woo |
—
|
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: April Woo | Statement: [Leslie Glass, fictionalDetectiveCreated, April Woo]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fictionalDetectiveCreated Context triple: [Leslie Glass, fictionalDetectiveCreated, April Woo]
-
A.
fictionalDetective
Indicates that the subject is a detective character who exists only in fiction rather than in real life.
-
B.
hasFictionalDetective
chosen
Indicates that one entity (typically a work or series) features or includes a fictional detective character as part of its content.
-
C.
fictionalInvention
Indicates that one entity is an invention or creation that exists only within the fictional context of another entity (such as a story, universe, or work).
-
D.
fictionalOrigin
Indicates that one entity originates from, or was first introduced within, a fictional work, universe, or narrative created by another entity.
-
E.
fictionalAuthorVictim
Indicates that one entity is the author of a fictional work in which the other entity appears as a victim.
- 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_69ee9d0024b8819090a7c8cf669a3b6c |
completed | April 26, 2026, 11:17 p.m. |
| NER | Named-entity recognition | batch_69f67f0488bc819089fbd2d2478158d3 |
completed | May 2, 2026, 10:47 p.m. |
| PD | Predicate disambiguation | batch_69f67e3ed894819094c067c1ef624951 |
completed | May 2, 2026, 10:44 p.m. |
Created at: April 27, 2026, 2:29 a.m.