Triple
T739436
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Darwin (civil servant) |
E15209
|
entity |
| Predicate | methodOfDisappearance |
P19454
|
FINISHED |
| Object | staged canoeing accident |
—
|
LITERAL 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: staged canoeing accident | Statement: [John Darwin (civil servant), methodOfDisappearance, staged canoeing accident]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: methodOfDisappearance Context triple: [John Darwin (civil servant), methodOfDisappearance, staged canoeing accident]
-
A.
disappearance
Indicates that an entity ceases to be present, visible, or detectable in a given context or location.
-
B.
yearOfDisappearance
Indicates the specific year in which an entity disappeared or ceased to be present.
-
C.
deathMethod
Indicates the specific way or means by which a death occurred.
-
D.
vanishesWhen
Indicates that one entity ceases to exist, be visible, or be present whenever a specified condition involving another entity holds.
-
E.
usedMethodOfKilling
Indicates that one entity employed a particular method or means to carry out a killing of another entity.
- F. None of above. chosen
Provenance (4 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_69a49358aa308190adbc9b5a0a2adcf9 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a64adf2c81908e48090be35dd9d9 |
completed | March 1, 2026, 8:49 p.m. |
| PD | Predicate disambiguation | batch_69a4a4fc734c81908fbd36386d5746d6 |
completed | March 1, 2026, 8:43 p.m. |
| PDg | Predicate description generation | batch_69a4a64957ec81909fe2e2dbffd80ed3 |
completed | March 1, 2026, 8:49 p.m. |
Created at: March 1, 2026, 7:37 p.m.