Triple
T7786992
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aurélia Thierrée |
E187270
|
entity |
| Predicate | grandmother |
P3524
|
FINISHED |
| Object | Oona O’Neill |
E27480
|
NE FINISHED |
How this triple was built (2 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: Oona O’Neill | Statement: [Aurélia Thierrée, grandmother, Oona O’Neill]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Oona O’Neill Context triple: [Aurélia Thierrée, grandmother, Oona O’Neill]
-
A.
Oona O’Neill
chosen
Oona O’Neill was an American-born actress and socialite, the daughter of playwright Eugene O’Neill, who became widely known as the longtime wife and muse of filmmaker Charlie Chaplin.
-
B.
Evelyn O'Neill
Evelyn O'Neill is a film producer best known for her work on acclaimed independent movies such as the coming-of-age drama "Lady Bird."
-
C.
Florence O'Callaghan
Florence O'Callaghan was the wife of renowned Victorian stage actor and theatre manager Sir Henry Irving.
-
D.
Deirdre Flynn
Deirdre Flynn is the daughter of famed Hollywood swashbuckling actor Errol Flynn.
-
E.
Elinor Donahue
Elinor Donahue is an American actress best known for her work in classic television sitcoms of the 1950s and 1960s.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca82af2d2c8190963861f5e0b8bf21 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cadf2462248190863f838f0e077923 |
completed | March 30, 2026, 8:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69caf6123ad48190a50339073e91748c |
completed | March 30, 2026, 10:15 p.m. |
Created at: March 30, 2026, 4:24 p.m.