Triple
T15059579
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bad Lieutenant |
E379589
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object |
Zoë Lund
Zoë Lund was an American actress, writer, and musician best known for her work in provocative independent films and her collaboration with director Abel Ferrara.
|
E1155324
|
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: Zoë Lund | Statement: [Bad Lieutenant, screenwriter, Zoë Lund]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zoë Lund Context triple: [Bad Lieutenant, screenwriter, Zoë Lund]
-
A.
Zoë Telford
Zoë Telford is a British actress known for her work in television dramas and comedies, including roles in series such as Sherlock and Teachers.
-
B.
Zoe Zimmer
Zoe Zimmer is the daughter of renowned film composer Hans Zimmer.
-
C.
Zoe Reynolds
Zoe Reynolds is a fictional MI5 intelligence officer and key member of the counter-terrorism team in the British television drama series "Spooks."
-
D.
Zoe Glazer
Zoe Glazer is a member of the prominent Glazer family, known for its extensive business interests and ownership stakes in major sports franchises.
-
E.
Zoe Colletti
Zoe Colletti is an American actress known for her roles in film and television, including horror and drama projects such as "Scary Stories to Tell in the Dark" and "Fear the Walking Dead."
- 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: Zoë Lund Triple: [Bad Lieutenant, screenwriter, Zoë Lund]
Generated description
Zoë Lund was an American actress, writer, and musician best known for her work in provocative independent films and her collaboration with director Abel Ferrara.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Zoë Lund Target entity description: Zoë Lund was an American actress, writer, and musician best known for her work in provocative independent films and her collaboration with director Abel Ferrara.
-
A.
Zoë Telford
Zoë Telford is a British actress known for her work in television dramas and comedies, including roles in series such as Sherlock and Teachers.
-
B.
Zoe Zimmer
Zoe Zimmer is the daughter of renowned film composer Hans Zimmer.
-
C.
Zoe Reynolds
Zoe Reynolds is a fictional MI5 intelligence officer and key member of the counter-terrorism team in the British television drama series "Spooks."
-
D.
Zoe Glazer
Zoe Glazer is a member of the prominent Glazer family, known for its extensive business interests and ownership stakes in major sports franchises.
-
E.
Zoe Colletti
Zoe Colletti is an American actress known for her roles in film and television, including horror and drama projects such as "Scary Stories to Tell in the Dark" and "Fear the Walking Dead."
- 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_69d85cd64d108190853797a95c11cc45 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69dedee50afc8190bf7b0f4bbe8c60a3 |
completed | April 15, 2026, 12:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff1337412081909f683ed542699ed5 |
completed | May 9, 2026, 10:57 a.m. |
| NEDg | Description generation | batch_69ff15c9898081909d60aad92f0ca85a |
completed | May 9, 2026, 11:08 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ff166bbe908190967e8a08e4505753 |
completed | May 9, 2026, 11:11 a.m. |
Created at: April 10, 2026, 3:01 a.m.