Triple
T2374540
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USS Lexington (CV-2) |
E46165
|
entity |
| Predicate | conversionFrom |
P5574
|
FINISHED |
| Object | battlecruiser hull |
—
|
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: battlecruiser hull | Statement: [USS Lexington (CV-2), conversionFrom, battlecruiser hull]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: conversionFrom Context triple: [USS Lexington (CV-2), conversionFrom, battlecruiser hull]
-
A.
convertedFrom
chosen
Indicates that one entity has been transformed or changed in form, type, or representation from another entity.
-
B.
convertedBy
Indicates that one entity has been transformed or changed in form, state, or representation through the action or process performed by another entity.
-
C.
convertsFrom
Indicates that one entity is transformed or changed into another entity, with the source being the starting form or state.
-
D.
conversionContext
Indicates the situational or environmental factors under which a conversion (e.g., change of state, format, or belief) occurs or is interpreted.
-
E.
convertsTo
Indicates that one entity is transformed or changed into another entity, typically resulting in a different state, form, or representation.
- 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_69a88a145268819083e2736cb835c696 |
completed | March 4, 2026, 7:37 p.m. |
| NER | Named-entity recognition | batch_69abca4d89248190be7d712d5fa8382b |
completed | March 7, 2026, 6:48 a.m. |
| PD | Predicate disambiguation | batch_69abc59d82f08190b7c36982d1ae783d |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:56 p.m.