Triple
T8996520
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anthony Darwin |
E214928
|
entity |
| Predicate | father |
P120
|
FINISHED |
| Object | John Darwin |
E421559
|
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: John Darwin | Statement: [Anthony Darwin, father, John Darwin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Darwin Context triple: [Anthony Darwin, father, John Darwin]
-
A.
John Darwin
chosen
John Darwin is a British former teacher and prison officer who infamously faked his own death in a canoeing accident in 2002 as part of an insurance fraud scheme.
-
B.
John Darwin
John Darwin is a British historian and academic known for his influential work on the history of empires, particularly the British Empire and global imperialism.
-
C.
Ian Darwin
Ian Darwin is a software developer and author best known for his contributions to Unix, Java, and open source programming resources.
-
D.
Geoffrey Simpson
Geoffrey Simpson is an Australian cinematographer known for his work on feature films including the 1994 adaptation of "Little Women."
-
E.
Mark Darwin
Mark Darwin is one of the two sons of British former teacher and convicted fraudster John Darwin, who became widely known due to his father's infamous "canoe man" disappearance and insurance scam.
- 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_69ca83a05c608190bdfdbdb25e994b39 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc68df33c48190a5017426e59c0bc4 |
completed | April 1, 2026, 12:37 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfd0d586c881909090b424f6fd036f |
completed | April 3, 2026, 2:38 p.m. |
Created at: March 30, 2026, 7:04 p.m.