Triple
T22655326
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Company (2018 West End revival) |
E559207
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object |
Gavin Spokes
Gavin Spokes is a British stage and screen actor best known for his work in major West End productions and television dramas.
|
E1549276
|
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: Gavin Spokes | Statement: [Company (2018 West End revival), starring, Gavin Spokes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gavin Spokes Context triple: [Company (2018 West End revival), starring, Gavin Spokes]
-
A.
Gavin Wiesen
Gavin Wiesen is an American film director and screenwriter best known for writing and directing the coming-of-age drama "The Art of Getting By."
-
B.
Gavin Miller
Gavin Miller is a fictional character from the animated web series "Stacked."
-
C.
Gavin Miller
Gavin Miller is a person known primarily in relation to Heather Miller, about whom little widely documented public information is available.
-
D.
Gavin Vogel
Gavin Vogel is the son of journalist Lloyd Vogel, a character inspired by real-life writer Tom Junod in the film "A Beautiful Day in the Neighborhood."
-
E.
Gavin Scott
Gavin Scott is a British screenwriter and producer known for his work on fantasy and historical adaptations for film and television.
- 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: Gavin Spokes Triple: [Company (2018 West End revival), starring, Gavin Spokes]
Generated description
Gavin Spokes is a British stage and screen actor best known for his work in major West End productions and television dramas.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Gavin Spokes Target entity description: Gavin Spokes is a British stage and screen actor best known for his work in major West End productions and television dramas.
-
A.
Gavin Wiesen
Gavin Wiesen is an American film director and screenwriter best known for writing and directing the coming-of-age drama "The Art of Getting By."
-
B.
Gavin Miller
Gavin Miller is a fictional character from the animated web series "Stacked."
-
C.
Gavin Miller
Gavin Miller is a person known primarily in relation to Heather Miller, about whom little widely documented public information is available.
-
D.
Gavin Vogel
Gavin Vogel is the son of journalist Lloyd Vogel, a character inspired by real-life writer Tom Junod in the film "A Beautiful Day in the Neighborhood."
-
E.
Gavin Scott
Gavin Scott is a British screenwriter and producer known for his work on fantasy and historical adaptations for film and television.
- 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_69e245489dd88190b1f674acf61c8769 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1765b93dc8190a0357dd4b6ae524a |
completed | April 29, 2026, 3:09 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0b73e246408190b4cab82e6799f162 |
completed | May 18, 2026, 8:17 p.m. |
| NEDg | Description generation | batch_6a0b77402cf48190999a8e99f69bd480 |
completed | May 18, 2026, 8:32 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0b77c92d6081909abd6f1280dc22f7 |
completed | May 18, 2026, 8:34 p.m. |
Created at: April 17, 2026, 3:06 p.m.