Triple
T21252390
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kingpin |
E523775
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Vanessa Fisk |
—
|
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: Vanessa Fisk | Statement: [Kingpin, spouse, Vanessa Fisk]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vanessa Fisk Context triple: [Kingpin, spouse, Vanessa Fisk]
-
A.
Vanessa Fisk
chosen
Vanessa Fisk is a fictional character in Marvel Comics, best known as the cultured and morally conflicted wife of the crime lord Wilson Fisk, also known as the Kingpin.
-
B.
Violet Campbell
Violet Campbell was the wife of British character actor Nigel Bruce, known for his portrayal of Dr. Watson in the classic Sherlock Holmes films.
-
C.
Violet Jones
Violet Jones is the image-conscious, perfection-seeking advertising executive whose emotional and personal transformation drives the romantic comedy film "Nappily Ever After."
-
D.
Vicky Licorish
Vicky Licorish is a film and television producer known for her work on the adaptation of Andrea Levy’s novel "Small Island."
-
E.
Victoria Thaine
Victoria Thaine is an Australian actress and writer best known for her work in film and television, including roles in psychological horror and drama productions.
- 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_69e0b5146c108190adc9adb73e90abff |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7359f5b408190b951adddba83c97a |
completed | April 21, 2026, 8:30 a.m. |
Created at: April 16, 2026, 3:57 p.m.