Triple
T14226599
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Betty Comden |
E352634
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Steven Kyle |
E352634
|
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: Steven Kyle | Statement: [Betty Comden, spouse, Steven Kyle]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Steven Kyle Context triple: [Betty Comden, spouse, Steven Kyle]
-
A.
Steven Kyle
chosen
Steven Kyle is best known as the husband of acclaimed American lyricist and screenwriter Betty Comden.
-
B.
Eric Drimmer
Eric Drimmer was the first husband of Hungarian-American actress and socialite Eva Gabor.
-
C.
Steven Grant
Steven Grant is an American comic book writer best known for creating the graphic novel that inspired the film "2 Guns."
-
D.
Steven Grant
Steven Grant is one of the main identities of the Marvel Comics character Moon Knight, portrayed in the Marvel Cinematic Universe by Oscar Isaac.
-
E.
Rob Gordon
Rob Gordon is the obsessive, music-obsessed record store owner and narrator of the romantic comedy film "High Fidelity," known for cataloging his life and relationships through top-five lists.
- 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_69d8278a06e481908b5d6af0a8afe737 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de6228e53c8190abbe4e2d88a7362a |
completed | April 14, 2026, 3:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd281801488190bcb17d27ee18cde6 |
completed | May 8, 2026, 12:02 a.m. |
Created at: April 10, 2026, 1:07 a.m.