Triple
T22189621
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Craig Jones |
E548381
|
entity |
| Predicate | hasSister |
P31639
|
FINISHED |
| Object | Dana Jones |
—
|
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: Dana Jones | Statement: [Craig Jones, hasSister, Dana Jones]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dana Jones Context triple: [Craig Jones, hasSister, Dana Jones]
-
A.
Dana Jones
chosen
Dana Jones is a person known primarily as a relative of Craig Jones.
-
B.
Dana York
Dana York is an American woman best known as the widow of rock musician Tom Petty, whom she married in 2001 and remained with until his death.
-
C.
Dana Lyon
Dana Lyon was a writer whose work served as the basis for the film "The House on Telegraph Hill."
-
D.
Dana DeMuth
Dana DeMuth is a longtime Major League Baseball umpire who has officiated numerous postseason games, including multiple World Series.
-
E.
Dana Ballard
Dana Ballard is an American computer scientist and cognitive scientist known for his pioneering work in computational vision and models of human perception and cognition.
- 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_69e11e3e0c7c8190b30d278845e2497e |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12aac07d88190848c940863c0a0c7 |
completed | April 28, 2026, 9:46 p.m. |
Created at: April 16, 2026, 8:35 p.m.