Triple
T17720865
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Jay |
E442330
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Maria Jay |
—
|
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: Maria Jay | Statement: [John Jay, child, Maria Jay]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Maria Jay Context triple: [John Jay, child, Maria Jay]
-
A.
Maria Jay
chosen
Maria Jay was a member of the prominent Jay family of early American political and social life, known as the daughter of Sarah Livingston Jay and statesman John Jay.
-
B.
Jennifer Jayne
Jennifer Jayne was a British film and television actress known for her roles in 1950s and 1960s comedies and genre films.
-
C.
Jacqueline King
Jacqueline King is a British actress best known to many for her recurring role as Sylvia Noble, Donna Noble’s mother, in the revived Doctor Who television series.
-
D.
Laura Bristow
Laura Bristow is the assumed American identity of Russian spy Irina Derevko in the television series "Alias."
-
E.
Mary Junson
Mary Junson is a supporting character in the comedy film "Coming 2 America," connected to the royal family of Zamunda in the sequel’s storyline.
- 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_69d8b9ec79688190b86bdcef85a7b3aa |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4748520a881908dc3446d33236ff7 |
completed | April 19, 2026, 6:21 a.m. |
Created at: April 10, 2026, 10:07 a.m.