Triple
T15987566
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anna Devane |
E387735
|
entity |
| Predicate | romanticPartner |
P9994
|
FINISHED |
| Object |
David Hayward
David Hayward is a fictional, often morally ambiguous cardiologist and longtime antagonist from the soap opera "All My Children."
|
E1190434
|
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: David Hayward | Statement: [Anna Devane, romanticPartner, David Hayward]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Hayward Context triple: [Anna Devane, romanticPartner, David Hayward]
-
A.
David Hay
David Hay is a New Zealand architect best known as a founding partner of the Auckland-based firm Mott, Hay and Anderson.
-
B.
Sam Hayward
Sam Hayward is an acclaimed American chef best known for his pioneering farm-to-table cuisine and leadership at the renowned Portland, Maine restaurant Fore Street.
-
C.
Dan Hayhurst
Dan Hayhurst is a Canadian contractor and bodyguard known for his brief marriage to actress and model Pamela Anderson.
-
D.
David Heath
David Heath is an American mixed martial artist who competed in the UFC’s light heavyweight division during the mid-2000s.
-
E.
David Hewitt
David Hewitt is a renowned mobile recording engineer and producer known for capturing high-profile live performances and concerts.
- 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: David Hayward Triple: [Anna Devane, romanticPartner, David Hayward]
Generated description
David Hayward is a fictional, often morally ambiguous cardiologist and longtime antagonist from the soap opera "All My Children."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: David Hayward Target entity description: David Hayward is a fictional, often morally ambiguous cardiologist and longtime antagonist from the soap opera "All My Children."
-
A.
David Hay
David Hay is a New Zealand architect best known as a founding partner of the Auckland-based firm Mott, Hay and Anderson.
-
B.
Sam Hayward
Sam Hayward is an acclaimed American chef best known for his pioneering farm-to-table cuisine and leadership at the renowned Portland, Maine restaurant Fore Street.
-
C.
Dan Hayhurst
Dan Hayhurst is a Canadian contractor and bodyguard known for his brief marriage to actress and model Pamela Anderson.
-
D.
David Heath
David Heath is an American mixed martial artist who competed in the UFC’s light heavyweight division during the mid-2000s.
-
E.
David Hewitt
David Hewitt is a renowned mobile recording engineer and producer known for capturing high-profile live performances and concerts.
- 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_69d86daa562c81908aacc179c0fe8fb5 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1575993948190a05d60fc9d0c05fa |
completed | April 16, 2026, 9:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffcf1cb1388190b1ebccc6705e5974 |
completed | May 10, 2026, 12:19 a.m. |
| NEDg | Description generation | batch_69ffcf9d6c5c8190b10abdf70aed7ddf |
completed | May 10, 2026, 12:21 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ffd96de9288190ab1727e7864dcaa6 |
completed | May 10, 2026, 1:03 a.m. |
Created at: April 10, 2026, 4:54 a.m.