Triple
T7520834
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Robinson |
E177763
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Robinson |
E75069
|
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: Robinson | Statement: [David Robinson, familyName, Robinson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Robinson Context triple: [David Robinson, familyName, Robinson]
-
A.
Robinson
chosen
Robinson is a common English surname borne by numerous notable figures across politics, sports, arts, and other fields.
-
B.
Crusoe Kurddal
Crusoe Kurddal is an Indigenous Australian actor best known for his role in the acclaimed film "Ten Canoes."
-
C.
Crusoe
Crusoe is a family of low-power x86-compatible microprocessors developed by Transmeta, known for using code-morphing software to translate x86 instructions to a VLIW core.
-
D.
Alexander Selkirk
Alexander Selkirk was a Scottish sailor famously marooned on a Pacific island in the early 18th century, whose real-life survival story helped inspire Daniel Defoe’s novel "Robinson Crusoe."
-
E.
James Crabe
James Crabe was an American cinematographer best known for his work on influential films of the 1970s and 1980s, including the original Rocky.
- 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_69c69f2891148190a484f3b8222c6f1b |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f7c2ad6c8190b822c0a5b80e7829 |
completed | March 27, 2026, 9:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c84629f00c8190a64d51586bd3b96c |
completed | March 28, 2026, 9:20 p.m. |
Created at: March 27, 2026, 3:46 p.m.