Triple
T33942676
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Discovery (ship) |
E870206
|
entity |
| Predicate | alongsideShip |
P177949
|
FINISHED |
| Object | Susan Constant |
—
|
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: Susan Constant | Statement: [Discovery (ship), alongsideShip, Susan Constant]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: alongsideShip Context triple: [Discovery (ship), alongsideShip, Susan Constant]
-
A.
assistedShip
Indicates that one entity helped or supported a ship in performing an operation, task, or journey.
-
B.
aboardShip
Indicates that one entity is physically on or inside a ship, typically as a passenger, crew member, or cargo.
-
C.
builtAlongside
Indicates that one entity was constructed next to or in parallel with another entity, typically during the same or a closely related time period.
-
D.
shipCompanion
Indicates that one entity serves as a companion or partner accompanying another entity on a ship or sea voyage.
-
E.
boatSide
Indicates that one entity is located on or associated with a particular side of a boat relative to another reference point or entity.
- F. None of above. chosen
Provenance (4 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_69f3499b0dd48190b07b4b60babcee02 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7064e906881909c3186c646145d34 |
completed | May 3, 2026, 8:24 a.m. |
| PD | Predicate disambiguation | batch_69f70100ec1c8190a6b97f50e88891f2 |
completed | May 3, 2026, 8:02 a.m. |
| PDg | Predicate description generation | batch_69f7064d37388190993b2a7305a02b9f |
completed | May 3, 2026, 8:24 a.m. |
Created at: May 1, 2026, 1:49 a.m.