Triple
T20629060
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | My First Wife |
E506900
|
entity |
| Predicate | hasCastMember |
P2308
|
FINISHED |
| Object |
Lucy Angwin
Lucy Angwin is an actress known for her role in the film "My First Wife."
|
E1440995
|
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: Lucy Angwin | Statement: [My First Wife, hasCastMember, Lucy Angwin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lucy Angwin Context triple: [My First Wife, hasCastMember, Lucy Angwin]
-
A.
Laura Harris
Laura Harris is a Canadian actress known for her roles in films like "The Faculty" and TV series such as "24" and "Dead Like Me."
-
B.
Angela Valamanesh
Angela Valamanesh is an Australian artist known for her evocative, often biomorphic sculptures and installations that explore themes of nature, science, and the human body.
-
C.
Amy B. Harris
Amy B. Harris is an American television writer and producer known for her work on series such as Sex and the City, The Carrie Diaries, and Designated Survivor.
-
D.
Nancy Millis
Nancy Millis was an influential Australian microbiologist and educator renowned for her pioneering work in industrial microbiology and for promoting science and biotechnology in Australia.
-
E.
Wendy Smith
Wendy Smith is known as the spouse of Argentine-born American singer and actor Dick Haymes, a prominent vocalist of the 1940s big band era.
- 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: Lucy Angwin Triple: [My First Wife, hasCastMember, Lucy Angwin]
Generated description
Lucy Angwin is an actress known for her role in the film "My First Wife."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Lucy Angwin Target entity description: Lucy Angwin is an actress known for her role in the film "My First Wife."
-
A.
Laura Harris
Laura Harris is a Canadian actress known for her roles in films like "The Faculty" and TV series such as "24" and "Dead Like Me."
-
B.
Angela Valamanesh
Angela Valamanesh is an Australian artist known for her evocative, often biomorphic sculptures and installations that explore themes of nature, science, and the human body.
-
C.
Amy B. Harris
Amy B. Harris is an American television writer and producer known for her work on series such as Sex and the City, The Carrie Diaries, and Designated Survivor.
-
D.
Nancy Millis
Nancy Millis was an influential Australian microbiologist and educator renowned for her pioneering work in industrial microbiology and for promoting science and biotechnology in Australia.
-
E.
Wendy Smith
Wendy Smith is known as the spouse of Argentine-born American singer and actor Dick Haymes, a prominent vocalist of the 1940s big band era.
- 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_69e0b4bd4a0081908d4e97a590a33fb2 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6abe771e88190a48471bf83b4804d |
completed | April 20, 2026, 10:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a08bb1fbaa48190a9299f137e3b3a62 |
completed | May 16, 2026, 6:44 p.m. |
| NEDg | Description generation | batch_6a08bbede37481909b842e99d4b29ed4 |
completed | May 16, 2026, 6:48 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a08bc6cc7a48190b6faba13514ec391 |
completed | May 16, 2026, 6:50 p.m. |
Created at: April 16, 2026, 11:42 a.m.