Triple
T9648995
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Faye Dunaway |
E233284
|
entity |
| Predicate | hasChild |
P369
|
FINISHED |
| Object |
Liam Dunaway O’Neill
Liam Dunaway O’Neill is the son of acclaimed American actress Faye Dunaway and photographer Terry O’Neill.
|
E811785
|
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: Liam Dunaway O’Neill | Statement: [Faye Dunaway, hasChild, Liam Dunaway O’Neill]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Liam Dunaway O’Neill Context triple: [Faye Dunaway, hasChild, Liam Dunaway O’Neill]
-
A.
Liam Sullivan
Liam Sullivan was an American character actor known for his numerous television and film roles from the 1950s through the 1980s, often portraying suave or villainous figures.
-
B.
Liam O’Connor
Liam O’Connor is a British architect best known for designing prominent public memorials, including the Bomber Command Memorial in London.
-
C.
Liam Lonergan
Liam Lonergan is an Irish businessman best known as one of the founders of the low-cost airline Ryanair.
-
D.
Luke Doolan
Luke Doolan is an Australian film editor and filmmaker best known for his work on acclaimed films such as "Animal Kingdom."
-
E.
Tim O'Connor
Tim O'Connor is a New Zealand educational leader best known for serving as rector of the prestigious Auckland Grammar School.
- 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: Liam Dunaway O’Neill Triple: [Faye Dunaway, hasChild, Liam Dunaway O’Neill]
Generated description
Liam Dunaway O’Neill is the son of acclaimed American actress Faye Dunaway and photographer Terry O’Neill.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Liam Dunaway O’Neill Target entity description: Liam Dunaway O’Neill is the son of acclaimed American actress Faye Dunaway and photographer Terry O’Neill.
-
A.
Liam Sullivan
Liam Sullivan was an American character actor known for his numerous television and film roles from the 1950s through the 1980s, often portraying suave or villainous figures.
-
B.
Liam O’Connor
Liam O’Connor is a British architect best known for designing prominent public memorials, including the Bomber Command Memorial in London.
-
C.
Liam Lonergan
Liam Lonergan is an Irish businessman best known as one of the founders of the low-cost airline Ryanair.
-
D.
Luke Doolan
Luke Doolan is an Australian film editor and filmmaker best known for his work on acclaimed films such as "Animal Kingdom."
-
E.
Tim O'Connor
Tim O'Connor is a New Zealand educational leader best known for serving as rector of the prestigious Auckland Grammar School.
- 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_69ca848b31648190b57aa55da20285be |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9bac55b48190ab2a8f9bb83c951e |
completed | April 1, 2026, 10:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d18262dc50819089cfc17c770a1a90 |
completed | April 4, 2026, 9:28 p.m. |
| NEDg | Description generation | batch_69d183452244819080de72fda8e14e67 |
completed | April 4, 2026, 9:31 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d183d506b881909375aadaaa616386 |
completed | April 4, 2026, 9:34 p.m. |
Created at: March 30, 2026, 8:13 p.m.