Triple
T16535857
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tsurugizaki |
E401687
|
entity |
| Predicate | convertedRole |
P72233
|
FINISHED |
| Object | aircraft carrier |
—
|
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: aircraft carrier | Statement: [Tsurugizaki, convertedRole, aircraft carrier]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: convertedRole Context triple: [Tsurugizaki, convertedRole, aircraft carrier]
-
A.
conversionRole
Indicates the specific role or function an entity plays within a conversion process or event.
-
B.
covertRole
Indicates that an entity holds or performs a hidden, secret, or undercover role in relation to another entity or context.
-
C.
representedRole
Indicates that one entity serves as a stand-in, proxy, or representative performing a role on behalf of another entity.
-
D.
roleAfterConversion
chosen
Indicates the role or position an entity holds after undergoing a conversion, transition, or change from a previous state or role.
-
E.
exportRole
Indicates that an entity functions in a capacity or role specifically related to exporting goods, services, or data.
- 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_69d88384bc30819084229e7dcdc39a41 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e345574d88819094548367bf983078 |
completed | April 18, 2026, 8:48 a.m. |
| PD | Predicate disambiguation | batch_69e2969fab208190ad64164d24748c45 |
completed | April 17, 2026, 8:22 p.m. |
Created at: April 10, 2026, 5:15 a.m.