Triple
T18609897
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Conrad Hilton |
E454863
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Mary Frances Kelly |
—
|
NE NERFINISHED |
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: Mary Frances Kelly | Statement: [Conrad Hilton, spouse, Mary Frances Kelly]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mary Frances Kelly Context triple: [Conrad Hilton, spouse, Mary Frances Kelly]
-
A.
Mary Frances Kelly
chosen
Mary Frances Kelly was the first wife of American hotel magnate Conrad Hilton, with whom she had several children before their divorce.
-
B.
Mary Amelia Rogers
Mary Amelia Rogers was a daughter of American humorist and social commentator Will Rogers, belonging to his prominent early 20th-century Oklahoma-based family.
-
C.
Mary Rice
Mary Rice is a personal name that may refer to multiple individuals, including historical or contemporary figures, depending on the context.
-
D.
Margaret Petit
Margaret Petit is the grandmother of actress Jennifer Hall.
-
E.
Marian Marsh
Marian Marsh was a Canadian-born American film actress best known for her leading roles in early 1930s Hollywood dramas and crime films.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8d38bbe7c8190bdec3138e7d413c9 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e54d0048b08190a7dd407f14d95799 |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 10, 2026, 11:45 a.m.