Triple
T5107757
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amy |
E115139
|
entity |
| Predicate | cinematographyBy |
P1953
|
FINISHED |
| Object |
Matt Curtis
Matt Curtis is a cinematographer known for his work on the film "Amy."
|
E526676
|
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: Matt Curtis | Statement: [Amy, cinematographyBy, Matt Curtis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Matt Curtis Context triple: [Amy, cinematographyBy, Matt Curtis]
-
A.
Jake Curtis
Jake Curtis is a British filmmaker and photographer, known as the son of screenwriter-director Richard Curtis and broadcaster Emma Freud.
-
B.
Matt Fenton
Matt Fenton is a British theatre director and arts leader known for his innovative, youth-focused programming and leadership within the UK performing arts sector.
-
C.
Curtis Craig
Curtis Craig was the male college student who served as the named plaintiff challenging Oklahoma's gender-based drinking age law in the landmark U.S. Supreme Court case Craig v. Boren.
-
D.
Brian Routh
Brian Routh was a British performance artist and musician best known as one half of the avant-garde comedy and performance duo The Kipper Kids.
-
E.
Matt Hulett
Matt Hulett is an American technology and business executive known for leading and scaling multiple software and digital media companies.
- 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: Matt Curtis Triple: [Amy, cinematographyBy, Matt Curtis]
Generated description
Matt Curtis is a cinematographer known for his work on the film "Amy."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Matt Curtis Target entity description: Matt Curtis is a cinematographer known for his work on the film "Amy."
-
A.
Jake Curtis
Jake Curtis is a British filmmaker and photographer, known as the son of screenwriter-director Richard Curtis and broadcaster Emma Freud.
-
B.
Matt Fenton
Matt Fenton is a British theatre director and arts leader known for his innovative, youth-focused programming and leadership within the UK performing arts sector.
-
C.
Curtis Craig
Curtis Craig was the male college student who served as the named plaintiff challenging Oklahoma's gender-based drinking age law in the landmark U.S. Supreme Court case Craig v. Boren.
-
D.
Brian Routh
Brian Routh was a British performance artist and musician best known as one half of the avant-garde comedy and performance duo The Kipper Kids.
-
E.
Matt Hulett
Matt Hulett is an American technology and business executive known for leading and scaling multiple software and digital media companies.
- 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_69bd4440b3348190be1251fd8b7951f1 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd75a8ee7881908876859402911e5a |
completed | March 20, 2026, 4:28 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bfc60964c08190bcb128946e121bc9 |
completed | March 22, 2026, 10:35 a.m. |
| NEDg | Description generation | batch_69bfc66e471c8190988fee5cd7fead5f |
completed | March 22, 2026, 10:37 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69bfc6c607b88190818e5a607313cc40 |
completed | March 22, 2026, 10:39 a.m. |
Created at: March 20, 2026, 1:41 p.m.