Triple
T23406584
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Rayburn |
E559950
|
entity |
| Predicate | hasSibling |
P363
|
FINISHED |
| Object | Danny Rayburn |
—
|
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: Danny Rayburn | Statement: [John Rayburn, hasSibling, Danny Rayburn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Danny Rayburn Context triple: [John Rayburn, hasSibling, Danny Rayburn]
-
A.
Danny Rayburn
chosen
Danny Rayburn is a central, troubled member of the Rayburn family whose dark past and destructive choices drive much of the drama in the TV series "Bloodline."
-
B.
Don Burnett
Don Burnett was a British-born American actor best known for his film and television roles in the 1950s and 1960s.
-
C.
Ray Sheppard
Ray Sheppard is a retired Canadian right winger who played over 800 NHL games and was known for his goal-scoring ability, including a 52-goal season with the Detroit Red Wings.
-
D.
Ric Binkley
Ric Binkley was an American illustrator best known for his science fiction and fantasy cover art in the mid-20th century.
-
E.
Bobby Duncan
Bobby Duncan is a musician best known as a member of the influential proto-punk band Death.
- 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_69e2454b3a5881909c64773dc8a5d289 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1a50e607c8190ba0a22e89862a2d9 |
completed | April 29, 2026, 6:28 a.m. |
Created at: April 17, 2026, 5:38 p.m.