Triple
T13646773
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary Frances Reynolds |
E326122
|
entity |
| Predicate | parent |
P120
|
FINISHED |
| Object | Maxine Harmon |
E733668
|
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: Maxine Harmon | Statement: [Mary Frances Reynolds, parent, Maxine Harmon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Maxine Harmon Context triple: [Mary Frances Reynolds, parent, Maxine Harmon]
-
A.
Maxine Harmon
chosen
Maxine Harmon is the child of Mary Frances Reynolds, better known as the actress Debbie Reynolds.
-
B.
Maxine Brown
Maxine Brown is an American soul and R&B singer best known for her 1960s hits like "All in My Mind" and "Funny," which helped define the early soul sound.
-
C.
Maxine Cooper
Maxine Cooper was an American actress best known for her role as Velda, the loyal secretary in the classic 1955 film noir "Kiss Me Deadly."
-
D.
Maxine Roby
Maxine Roby is a central forensic crime lab leader in the television series "CSI: Vegas," known for her sharp investigative skills and authoritative presence.
-
E.
Maxine Sneed
Maxine Sneed is a Canadian editor and the former wife of comedian and actor Tommy Chong.
- 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_69d8076beddc8190a53156f5bea77f5e |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbc6073e888190965456a639839749 |
completed | April 12, 2026, 4:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd4c20e45c8190968a5d88a2b3fe37 |
completed | May 8, 2026, 2:36 a.m. |
Created at: April 9, 2026, 9:52 p.m.