Triple
T20361113
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spun |
E496781
|
entity |
| Predicate | cinematographer |
P1953
|
FINISHED |
| Object |
Eric Broms
Eric Broms is a cinematographer known for his work on the film "Spun" and other visually distinctive projects.
|
E1427374
|
NE FINISHED |
How this triple was built (4 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: Eric Broms | Statement: [Spun, cinematographer, Eric Broms]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eric Broms Context triple: [Spun, cinematographer, Eric Broms]
-
A.
Eric Bernt
Eric Bernt is an American screenwriter known for his work on action and thriller films, including the 2000 martial arts crime movie "Romeo Must Die."
-
B.
Eric Bergstol
Eric Bergstol is an American golf course architect known for designing high-end, links-style courses in the New York metropolitan area.
-
C.
Eric Bernthal
Eric Bernthal is an American lawyer and former chair of the Humane Society of the United States, best known as the father of actor Jon Bernthal.
-
D.
Erik Josten
Erik Josten is a Marvel Comics supervillain-turned-antihero known for his immense strength and size-changing powers under various aliases, including Power Man, Goliath, and Atlas.
-
E.
Erik Barmack
Erik Barmack is a film and television producer and former Netflix executive known for developing and overseeing international original content.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Eric Broms Triple: [Spun, cinematographer, Eric Broms]
Generated description
Eric Broms is a cinematographer known for his work on the film "Spun" and other visually distinctive projects.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Eric Broms Target entity description: Eric Broms is a cinematographer known for his work on the film "Spun" and other visually distinctive projects.
-
A.
Eric Bernt
Eric Bernt is an American screenwriter known for his work on action and thriller films, including the 2000 martial arts crime movie "Romeo Must Die."
-
B.
Eric Bergstol
Eric Bergstol is an American golf course architect known for designing high-end, links-style courses in the New York metropolitan area.
-
C.
Eric Bernthal
Eric Bernthal is an American lawyer and former chair of the Humane Society of the United States, best known as the father of actor Jon Bernthal.
-
D.
Erik Josten
Erik Josten is a Marvel Comics supervillain-turned-antihero known for his immense strength and size-changing powers under various aliases, including Power Man, Goliath, and Atlas.
-
E.
Erik Barmack
Erik Barmack is a film and television producer and former Netflix executive known for developing and overseeing international original content.
- F. None of above. chosen
Provenance (5 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_69e0b4a3f7f48190b37f354574028ca6 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6786de5988190827584358c9db147 |
completed | April 20, 2026, 7:03 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a08761089a0819088d14d6fe7922669 |
completed | May 16, 2026, 1:50 p.m. |
| NEDg | Description generation | batch_6a087709e00c81908b564de6a00798ae |
completed | May 16, 2026, 1:54 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0877bd84d08190b22722b247c92f8d |
completed | May 16, 2026, 1:57 p.m. |
Created at: April 16, 2026, 11:25 a.m.