Triple
T22451200
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shoresy |
E554993
|
entity |
| Predicate | originalNetwork |
P2594
|
FINISHED |
| Object | Crave |
—
|
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: Crave | Statement: [Shoresy, originalNetwork, Crave]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Crave Context triple: [Shoresy, originalNetwork, Crave]
-
A.
Crave
chosen
Crave is a Canadian premium television and streaming service known for offering a wide range of movies, original series, and popular TV content.
-
B.
Craving
"Craving" is a soulful pop-rock song by James Bay that showcases his emotive vocals and introspective songwriting.
-
C.
Insaciable
Insaciable is a 1976 Argentine erotic drama film starring Isabel Sarli, known for its provocative themes and iconic status in Latin American cult cinema.
-
D.
Craze
Craze is an English surname most notably associated with actor Michael Craze, known for his role in the classic television series Doctor Who.
-
E.
Cravings: Hungry for More
Cravings: Hungry for More is a bestselling cookbook of indulgent, flavor-packed recipes co-authored by Adeena Sussman with Chrissy Teigen.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e5113208190ab58c6b595f9d1d0 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15b4ba6a88190a0a79e2c20fa8c08 |
completed | April 29, 2026, 1:13 a.m. |
Created at: April 16, 2026, 8:48 p.m.