Triple
T27780371
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sea Gale Fishing Company |
E699318
|
entity |
| Predicate | associatedWithMaritimeDisaster |
P166196
|
FINISHED |
| Object | loss of Andrea Gail |
—
|
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: loss of Andrea Gail | Statement: [Sea Gale Fishing Company, associatedWithMaritimeDisaster, loss of Andrea Gail]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedWithMaritimeDisaster Context triple: [Sea Gale Fishing Company, associatedWithMaritimeDisaster, loss of Andrea Gail]
-
A.
shipwreckInvolved
Indicates that an entity was involved in a shipwreck event, either as a participant, cause, or affected object.
-
B.
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.
-
C.
shipwreckUse
Indicates that an entity makes use of, interacts with, or derives benefit from a shipwreck.
-
D.
maritimeIncident
chosen
Indicates an event or situation involving a vessel or maritime activity that results in damage, danger, or disruption at sea or in navigable waters.
-
E.
accompaniedByAtSinking
Indicates that one entity was present with and accompanying another entity at the time the latter sank.
- 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_69ef6a4b5a9081909c9111396c2be3d2 |
completed | April 27, 2026, 1:53 p.m. |
| NER | Named-entity recognition | batch_6a00694f72888190983fee7d687a6daa |
completed | May 10, 2026, 11:17 a.m. |
| PD | Predicate disambiguation | batch_6a00685dbf44819098ea0c86bb9e50d8 |
completed | May 10, 2026, 11:13 a.m. |
Created at: April 27, 2026, 5:09 p.m.