Triple
T15683344
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heather Kadin |
E377633
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | Bad Robot Productions |
E85542
|
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: Bad Robot Productions | Statement: [Heather Kadin, employer, Bad Robot Productions]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bad Robot Productions Context triple: [Heather Kadin, employer, Bad Robot Productions]
-
A.
Bad Robot Productions
chosen
Bad Robot Productions is an American film and television production company known for creating popular genre franchises and series such as Lost, Alias, and the recent Star Trek and Star Wars films.
-
B.
Amen Ra Films
Amen Ra Films is a film production company founded by Wesley Snipes, best known for producing projects such as the action-horror sequel "Blade II."
-
C.
Relativity Productions
Relativity Productions is a film production company known for backing a range of American feature films across genres.
-
D.
Davros Films
Davros Films is a film production company best known for producing the apartheid-era drama "A Dry White Season."
-
E.
Alcor Films
Alcor Films is a film production company best known for producing the 1994 legal thriller "The Client."
- 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_69d85cd2e28481909d4e975bee20872f |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04f31b5b881908e46ecd9fc6048ab |
completed | April 16, 2026, 2:53 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff6ee4c8688190ae2fefb56171161a |
completed | May 9, 2026, 5:29 p.m. |
Created at: April 10, 2026, 4:17 a.m.