Triple
T20239724
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emma Booth |
E498249
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Marie Booth |
—
|
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: Marie Booth | Statement: [Emma Booth, sibling, Marie Booth]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marie Booth Context triple: [Emma Booth, sibling, Marie Booth]
-
A.
Marie Booth
chosen
Marie Booth was a daughter of William Booth, the founder of The Salvation Army, and a member of the prominent Booth family involved in the movement’s early work.
-
B.
Marie Drinkard
Marie Drinkard is a member of the Drinkard family, known for its deep roots in American gospel music and its connection to prominent singers like Cissy Houston and Whitney Houston.
-
C.
Marie Allison
Marie Allison was the wife of legendary American jazz drummer and bandleader Buddy Rich.
-
D.
Estelle Booth
Estelle Booth was the wife of American film and television actor Grant Withers.
-
E.
Margaret Booth
Margaret Booth was a pioneering American film editor and longtime MGM supervising editor whose career spanned the silent era through Hollywood’s Golden Age.
- 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_69da6274c58c81909c646eabed6f4f30 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6716dd0b081909d4063150cdc0c02 |
completed | April 20, 2026, 6:33 p.m. |
Created at: April 11, 2026, 11:40 p.m.