Triple
T2422170
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Cassavetes |
E53441
|
entity |
| Predicate | directed |
P7373
|
FINISHED |
| Object | Faces |
E265073
|
NE FINISHED |
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: Faces | Statement: [John Cassavetes, directed, Faces]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Faces Context triple: [John Cassavetes, directed, Faces]
-
A.
Faces
chosen
Faces is a 1968 independent drama film written and directed by John Cassavetes, noted for its raw, improvisational style and intense exploration of marital breakdown and human relationships.
-
B.
Two Faces
Two Faces is a song by Bruce Springsteen from his 1987 album "Tunnel of Love," reflecting themes of inner conflict and emotional duality.
-
C.
Moon-Face
Moon-Face is a friendly, moon-faced resident of the Magic Faraway Tree in Enid Blyton’s children’s books, known for his whimsical personality and love of fun adventures.
-
D.
Smiles
Smiles is a Brazilian frequent-flyer and loyalty program that allows members to earn and redeem miles across flights, partner airlines, and various retail and service partners.
-
E.
Face ID
Face ID is Apple's facial recognition system that securely unlocks devices and authorizes actions like payments and app logins using a 3D scan of the user's face.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ab495c44d48190b7235b23719bc3f6 |
completed | March 6, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69abc971093481909c8924d58187860c |
completed | March 7, 2026, 6:45 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69aef0a299648190a55e9f2c47bd307f |
completed | March 9, 2026, 4:09 p.m. |
Created at: March 6, 2026, 9:42 p.m.