Triple
T3067780
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mara family |
E62147
|
entity |
| Predicate | hasMember |
P10
|
FINISHED |
| Object | John Mara |
E11249
|
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: John Mara | Statement: [Mara family, hasMember, John Mara]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Mara Context triple: [Mara family, hasMember, John Mara]
-
A.
John Mara
chosen
John Mara is an American sports executive best known as the longtime co-owner and president of the NFL’s New York Giants.
-
B.
Barry Gettleman
Barry Gettleman is the son of Estelle Scher, better known as actress Estelle Getty from the television series "The Golden Girls."
-
C.
Rex Ryan
Rex Ryan is an outspoken former NFL head coach best known for leading the New York Jets to consecutive AFC Championship Game appearances and for his fiery personality and defensive expertise.
-
D.
Jack Daboll
Jack Daboll is a member of the Daboll family, related to NFL head coach Brian Daboll.
-
E.
Todd Bowles
Todd Bowles is an American football coach and former NFL defensive back best known as the head coach of the Tampa Bay Buccaneers and previously the New York Jets.
- 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_69ad85793e5c8190a358049bc4a98d8c |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada0fea06881909e5251eea26599ac |
completed | March 8, 2026, 4:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b1ef1972e08190942a068c0c563e52 |
completed | March 11, 2026, 10:39 p.m. |
Created at: March 8, 2026, 3:02 p.m.