Triple
T22958858
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jenny Hart |
E570837
|
entity |
| Predicate | isMatriarchOf |
P9499
|
FINISHED |
| Object | Hart family |
—
|
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: Hart family | Statement: [Jenny Hart, isMatriarchOf, Hart family]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hart family Context triple: [Jenny Hart, isMatriarchOf, Hart family]
-
A.
Hart family
chosen
The Hart family is a prominent American entertainment family best known for including comedian and actor Kevin Hart and his children.
-
B.
Hart family
The Hart family is a prominent Canadian wrestling dynasty known for producing numerous influential professional wrestlers and trainers across multiple generations.
-
C.
Hart family
The Hart family is a prominent American political and social dynasty from Kentucky, known for producing influential figures in early U.S. history.
-
D.
Harper family
The Harper family is a prominent American publishing dynasty best known for establishing the influential publishing house that evolved into HarperCollins.
-
E.
Harrington family
The Harrington family is a benefactor family recognized for its significant philanthropic support to Boston College athletics.
- 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_69e245b212a88190b5259caf51606084 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f181f2ce9c8190977f146771816341 |
completed | April 29, 2026, 3:58 a.m. |
Created at: April 17, 2026, 3:47 p.m.