Triple
T19091886
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Judy Robinson |
E467306
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | John Robinson |
—
|
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: John Robinson | Statement: [Judy Robinson, relative, John Robinson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Robinson Context triple: [Judy Robinson, relative, John Robinson]
-
A.
John Robinson
John Robinson was an influential early 17th-century English Separatist pastor and theologian best known for guiding the Pilgrim Fathers who later founded Plymouth Colony in New England.
-
B.
John Robinson
John Robinson is an American football coach best known for leading the Los Angeles Rams in the NFL and the USC Trojans to multiple Rose Bowl victories.
-
C.
John Robinson
chosen
John Robinson is the fictional leader and father of the spacefaring Robinson family in the 1998 science fiction film "Lost in Space."
-
D.
John Robinson
John Robinson was the husband of Harlem Renaissance figure and businesswoman A'Lelia Walker, connecting him to the prominent Walker family legacy.
-
E.
John Robinson
John Robinson is an actor known for his role in the independent drama film "Wendy and Lucy."
- 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_69d8dd05ac4c8190b1967d8f97f3fb2f |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e34c22a08190bf34f92f727268c5 |
completed | April 20, 2026, 8:26 a.m. |
Created at: April 10, 2026, 12:04 p.m.