Triple
T36493483
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lexington-class aircraft carrier |
E899113
|
entity |
| Predicate | secondShipOfClass |
P75728
|
FINISHED |
| Object | USS Saratoga (CV-3) |
—
|
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 Saratoga (CV-3) | Statement: [Lexington-class aircraft carrier, secondShipOfClass, USS Saratoga (CV-3)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: secondShipOfClass Context triple: [Lexington-class aircraft carrier, secondShipOfClass, USS Saratoga (CV-3)]
-
A.
secondShip
chosen
Indicates that one entity is the second ship in an ordered sequence or ranking relative to another entity.
-
B.
secondBoat
Indicates that one entity is the second boat in a sequence or relative ordering with respect to another boat.
-
C.
secondShipRenamedAs
Indicates that a second ship has been given a new name, establishing a renaming relationship between its prior and current identities.
-
D.
isSecondOfClass
Indicates that an entity holds the second position or rank within a defined class, category, or ordered group.
-
E.
secondGenerationClass
Indicates that one entity is a second-generation class derived from or conceptually following an earlier, first-generation class.
- 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_69f76e5ad4588190bdbce60c52fbb785 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ff64b957bc81908afbc5914234a8ea |
completed | May 9, 2026, 4:45 p.m. |
| PD | Predicate disambiguation | batch_69ff6446593c81909173e296eea2590c |
completed | May 9, 2026, 4:43 p.m. |
Created at: May 3, 2026, 4:10 p.m.