Triple
T681048
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blood and Sand (1922 film) |
E13180
|
entity |
| Predicate | costumeDesignBy |
P184
|
FINISHED |
| Object |
Travis Banton
Travis Banton was a prominent American Hollywood costume designer best known for his glamorous, influential work at Paramount Pictures during the 1920s and 1930s.
|
E162934
|
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: Travis Banton | Statement: [Blood and Sand (1922 film), costumeDesignBy, Travis Banton]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Travis Banton Context triple: [Blood and Sand (1922 film), costumeDesignBy, Travis Banton]
-
A.
Travis Beacham
Travis Beacham is an American screenwriter best known for co-writing the science fiction monster film "Pacific Rim."
-
B.
Kyle Rote
Kyle Rote was a former New York Giants star running back and wide receiver who became a prominent American sportscaster and television commentator.
-
C.
Brent Thomas
Brent Thomas is an advertising professional best known for writing Apple’s iconic 1984 Super Bowl commercial.
-
D.
Brandon Scott
Brandon Scott is an American politician serving as the mayor of Baltimore, Maryland.
-
E.
Brian VanDeMark
Brian VanDeMark is an American historian and author known for his work on U.S. foreign policy and the Vietnam War, including coauthoring influential studies of that conflict.
- 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: Travis Banton Triple: [Blood and Sand (1922 film), costumeDesignBy, Travis Banton]
Generated description
Travis Banton was a prominent American Hollywood costume designer best known for his glamorous, influential work at Paramount Pictures during the 1920s and 1930s.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Travis Banton Target entity description: Travis Banton was a prominent American Hollywood costume designer best known for his glamorous, influential work at Paramount Pictures during the 1920s and 1930s.
-
A.
Travis Beacham
Travis Beacham is an American screenwriter best known for co-writing the science fiction monster film "Pacific Rim."
-
B.
Kyle Rote
Kyle Rote was a former New York Giants star running back and wide receiver who became a prominent American sportscaster and television commentator.
-
C.
Brent Thomas
Brent Thomas is an advertising professional best known for writing Apple’s iconic 1984 Super Bowl commercial.
-
D.
Brandon Scott
Brandon Scott is an American politician serving as the mayor of Baltimore, Maryland.
-
E.
Brian VanDeMark
Brian VanDeMark is an American historian and author known for his work on U.S. foreign policy and the Vietnam War, including coauthoring influential studies of that conflict.
- 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_69a4933d3bf88190972041cd8cf143b9 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a4a06e294c8190873116a3253e04f9 |
completed | March 1, 2026, 8:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad0132cd6081908d70112213343063 |
completed | March 8, 2026, 4:55 a.m. |
| NEDg | Description generation | batch_69ad018ec1fc81909fb4719ae30cb465 |
completed | March 8, 2026, 4:56 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ad020c59b08190a4bda7e9d3194fd9 |
completed | March 8, 2026, 4:58 a.m. |
Created at: March 1, 2026, 7:36 p.m.