Triple
T29760799
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rebecca Newt Jorden |
E753761
|
entity |
| Predicate | travelsAboard |
P122348
|
FINISHED |
| Object | USS Sulaco |
—
|
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: USS Sulaco | Statement: [Rebecca Newt Jorden, travelsAboard, USS Sulaco]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: travelsAboard Context triple: [Rebecca Newt Jorden, travelsAboard, USS Sulaco]
-
A.
travelsOn
Indicates that an entity moves or journeys using a particular route, path, or mode of transportation.
-
B.
traveledAs
Indicates that an entity moved from one place to another in the role, capacity, or identity specified by another entity (e.g., as a tourist, as a representative, as a refugee).
-
C.
journeyedWith
Indicates that one entity traveled or went on a journey together with another entity as companions.
-
D.
travelsInVehicle
chosen
Indicates that an entity is moving from one place to another while being transported inside or on a vehicle.
-
E.
travelsThrough
Indicates that something moves along, passes across, or is routed via a particular path, medium, or location.
- 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_69f0ef827ff88190ade56e0b0846b713 |
completed | April 28, 2026, 5:33 p.m. |
| NER | Named-entity recognition | batch_69f69dfdda708190be290c7bec205445 |
completed | May 3, 2026, 12:59 a.m. |
| PD | Predicate disambiguation | batch_69f69d1a37e081908d1d86b90ff502bd |
completed | May 3, 2026, 12:55 a.m. |
Created at: April 28, 2026, 8:32 p.m.