Triple
T35958831
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Edmund Fitzgerald shipwreck |
E1039940
|
entity |
| Predicate | destinationAtTimeOfLoss |
P127107
|
FINISHED |
| Object | Zug Island near Detroit, Michigan |
—
|
NE NERFINISHED |
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: Zug Island near Detroit, Michigan | Statement: [Edmund Fitzgerald shipwreck, destinationAtTimeOfLoss, Zug Island near Detroit, Michigan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: destinationAtTimeOfLoss Context triple: [Edmund Fitzgerald shipwreck, destinationAtTimeOfLoss, Zug Island near Detroit, Michigan]
-
A.
intendedDestinationAtAccident
chosen
Indicates that a location was the destination an entity was heading toward at the time an accident occurred.
-
B.
intendedDestinationAtTimeOfDisappearance
Indicates the location or place an entity was planning to go to at the specific time when it disappeared.
-
C.
locationBeforeTheft
Indicates the place where an entity was situated immediately prior to the theft event.
-
D.
residenceAfterAccident
Indicates that an entity’s place of residence following an accident is a specified location.
-
E.
positionDuringAccident
Indicates the spatial or situational position an entity occupied at the time an accident occurred.
- 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_69f76e26b21081909fd9ffb3aff6c77a |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7ac23d1388190bdf9628b294943bd |
completed | May 3, 2026, 8:12 p.m. |
| PD | Predicate disambiguation | batch_69f7ab734d848190a84f9b8c3a952b75 |
completed | May 3, 2026, 8:09 p.m. |
Created at: May 3, 2026, 4:07 p.m.