Triple
T17480659
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Josh Berman |
E425648
|
entity |
| Predicate | creatorOf |
P806
|
FINISHED |
| Object | Killer Women |
—
|
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: Killer Women | Statement: [Josh Berman, creatorOf, Killer Women]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Killer Women Context triple: [Josh Berman, creatorOf, Killer Women]
-
A.
Killer Women
chosen
Killer Women is an American crime drama television series that follows a tough female Texas Ranger as she investigates cases involving women accused of murder.
-
B.
Mujeres Asesinas
Mujeres Asesinas is a Latin American crime drama anthology series that portrays different women driven to commit murder, often inspired by real-life cases.
-
C.
Why Women Kill
Why Women Kill is a darkly comedic anthology drama series that explores the lives of women in different decades as they confront infidelity and its sometimes deadly consequences.
-
D.
When Women Kill
When Women Kill is a 1983 documentary film directed by Lee Grant that examines the lives and circumstances of women incarcerated for committing homicide.
-
E.
Ladykiller
"Ladykiller" is a moody, soulful rock song by The Horrible Crowes, the side project of The Gaslight Anthem’s Brian Fallon.
- 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_69d889dccf7481909264a1844a2e9100 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e451bf1e8081909f4d4b8992412e62 |
completed | April 19, 2026, 3:53 a.m. |
Created at: April 10, 2026, 5:48 a.m.