Triple
T22486844
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stealie |
E555906
|
entity |
| Predicate | relatedTo |
P37
|
FINISHED |
| Object | Steal Your Face |
—
|
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: Steal Your Face | Statement: [Stealie, relatedTo, Steal Your Face]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Steal Your Face Context triple: [Stealie, relatedTo, Steal Your Face]
-
A.
Steal Your Face
chosen
Steal Your Face is a live double album by the Grateful Dead, recorded during their mid-1970s performances and released in 1976.
-
B.
Stolen Face
Stolen Face is a 1952 British film noir melodrama in which Lizabeth Scott plays a woman whose surgically altered look-alike becomes the obsession of a disfigured plastic surgeon.
-
C.
That Face
"That Face" is a darkly comic stage play by Polly Stenham about a dysfunctional upper-middle-class British family, notable for its intense psychological drama and acclaimed London productions.
-
D.
Broken Face
"Broken Face" is a raw, punk-influenced track by the Pixies, featured on their influential 1988 album *Surfer Rosa*.
-
E.
Saving My Face
"Saving My Face" is a song by Scottish singer-songwriter KT Tunstall from her album *Drastic Fantastic*.
- 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_69e11e53897c819088863779f8c50bb0 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15c3da9588190abf2f96d3104edfb |
completed | April 29, 2026, 1:17 a.m. |
Created at: April 16, 2026, 8:49 p.m.