Triple
T14813932
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HMS Sirius |
E348259
|
entity |
| Predicate | causeOfWreck |
P27489
|
FINISHED |
| Object | grounded on reef |
—
|
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: grounded on reef | Statement: [HMS Sirius, causeOfWreck, grounded on reef]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: causeOfWreck Context triple: [HMS Sirius, causeOfWreck, grounded on reef]
-
A.
causeOfShipwreck
chosen
Indicates the factor, event, or condition that directly led to a shipwreck occurring.
-
B.
shipwreck
Indicates that a vessel has been destroyed, stranded, or severely damaged, typically at sea or near a shoreline.
-
C.
wreckSurveyedBy
Indicates that a particular wreck has been examined, measured, or documented by a specified surveying party or method.
-
D.
shipwreckEvent
Indicates an event in which a ship is destroyed, stranded, or severely damaged, typically resulting in loss or abandonment at sea or near a shoreline.
-
E.
wreckDiscovery
Indicates that an entity discovers, finds, or identifies a wreck (such as a ruined or destroyed object, vehicle, or structure).
- 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_69d822eb8f588190bf53445e730a934f |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69decfe0e89c81908c0e1fe2bc3ebcfc |
completed | April 14, 2026, 11:38 p.m. |
| PD | Predicate disambiguation | batch_69de8c0ef8a4819092d84478b1f56db1 |
completed | April 14, 2026, 6:48 p.m. |
Created at: April 10, 2026, 1:48 a.m.