Triple
T24176781
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tim McCarthy |
E599303
|
entity |
| Predicate | shipmateOf |
P37846
|
FINISHED |
| Object | Frank Worsley |
—
|
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: Frank Worsley | Statement: [Tim McCarthy, shipmateOf, Frank Worsley]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: shipmateOf Context triple: [Tim McCarthy, shipmateOf, Frank Worsley]
-
A.
shipCompanion
chosen
Indicates that one entity serves as a companion or partner accompanying another entity on a ship or sea voyage.
-
B.
shipsWith
Indicates that one entity is delivered, packaged, or provided together with another entity as part of the same shipment or bundle.
-
C.
sisterShip
Indicates that two ships are considered counterparts or equivalents, typically of the same design, class, or series.
-
D.
shipAssociatedWith
Indicates that there is a relevant connection or involvement between a ship and another entity, such as ownership, operation, registration, or functional association.
-
E.
hasShipRole
Indicates that an entity holds or is assigned a specific role or function on a ship.
- 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_69e288cca05481908faeb1563711114a |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f27c9ddfcc819096697a844b300cce |
completed | April 29, 2026, 9:48 p.m. |
| PD | Predicate disambiguation | batch_69f1c42f942c8190b103ff29a60fef34 |
completed | April 29, 2026, 8:41 a.m. |
Created at: April 17, 2026, 11:34 p.m.