Triple
T4096722
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Thief, His Wife and the Canoe |
E87838
|
entity |
| Predicate | hasRealWorldEventAsSubject |
P33853
|
FINISHED |
| Object | John Darwin canoe disappearance |
—
|
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: John Darwin canoe disappearance | Statement: [The Thief, His Wife and the Canoe, hasRealWorldEventAsSubject, John Darwin canoe disappearance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRealWorldEventAsSubject Context triple: [The Thief, His Wife and the Canoe, hasRealWorldEventAsSubject, John Darwin canoe disappearance]
-
A.
hasRealizationAs
Indicates that something abstract, such as a plan, design, or concept, is concretely implemented or manifested as a particular realized form.
-
B.
hadEvent
Indicates that an entity experienced, hosted, or was associated with a specific event at some point in time.
-
C.
basedOnEventsDescribedIn
chosen
Indicates that something is derived from, inspired by, or constructed using the events described in another source.
-
D.
mainEventFor
Indicates that one event is the primary or central event associated with another entity, such as a context, grouping, or larger occurrence.
-
E.
hasSideEvent
Indicates that an event is associated with an additional, related side event occurring alongside it.
- F. None of above.
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_69aed94564cc8190a9c1457daedb6e7f |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefcdef11081908c626a89f2c0e121 |
completed | March 9, 2026, 5:01 p.m. |
| PD | Predicate disambiguation | batch_69aef90b2ef08190ae84febfd69dd48b |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:40 p.m.