Triple
T13090053
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aline MacMahon |
E310437
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Aline MacMahon |
E310437
|
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: Aline MacMahon | Statement: [Aline MacMahon, name, Aline MacMahon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Aline MacMahon Context triple: [Aline MacMahon, name, Aline MacMahon]
-
A.
Aline MacMahon
chosen
Aline MacMahon was an American stage and film actress known for her sharp wit and character roles in early 20th-century Hollywood cinema.
-
B.
Clelia Mountford
Clelia Mountford is a television producer and executive known for her work on comedy projects, including serving as an executive producer on the animated series "HouseBroken."
-
C.
Muriel Fraser
Muriel Fraser was the wife of English poet Ralph Hodgson, a key figure in his personal life and literary milieu.
-
D.
Flora Hewlett
Flora Hewlett was a philanthropist whose legacy is honored through the naming of the William and Flora Hewlett Foundation, a major charitable organization.
-
E.
Lydia MacMillan
Lydia MacMillan is a fictional character named Lydia, likely serving as a central or significant figure in her narrative.
- 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_69d806a733548190989cfd4ce981ca33 |
completed | April 9, 2026, 8:05 p.m. |
| NER | Named-entity recognition | batch_69d98138a1d481908a139f2f67eb3472 |
completed | April 10, 2026, 11:01 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6f5cd9f2081908c207b21a14233e1 |
completed | May 3, 2026, 7:14 a.m. |
Created at: April 9, 2026, 9:03 p.m.