Triple
T36515217
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lexington-class battlecruiser |
E900016
|
entity |
| Predicate | plannedShip |
P193804
|
FINISHED |
| Object | USS Lexington (CC-1) |
—
|
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 Lexington (CC-1) | Statement: [Lexington-class battlecruiser, plannedShip, USS Lexington (CC-1)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: plannedShip Context triple: [Lexington-class battlecruiser, plannedShip, USS Lexington (CC-1)]
-
A.
shipPlanned
Indicates that an item or order is scheduled and intended to be shipped at a planned future time.
-
B.
numberOfPlannedShips
Indicates the total count of ships that are intended or scheduled to be built, deployed, or used according to a plan.
-
C.
targetedShip
Indicates that one entity has selected or designated a particular ship as the focus of its attention or action, such as for attack, tracking, or interaction.
-
D.
boardsShip
Indicates that one entity gets onto or enters a ship as a passenger or crew member.
-
E.
otherPlannedBoats
Indicates that there are additional boats, beyond the primary one(s) referenced, that are planned or scheduled in relation to the same context or event.
- 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_69f76e5dada881909da2d34bc7a9202a |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fd553d7cb881908d243e7a9f30ac85 |
completed | May 8, 2026, 3:15 a.m. |
| PD | Predicate disambiguation | batch_69fd514dcb1c81908333c70d7edd79c9 |
completed | May 8, 2026, 2:58 a.m. |
| PDg | Predicate description generation | batch_69fd553c01488190b9fda48b4a728f04 |
completed | May 8, 2026, 3:15 a.m. |
Created at: May 3, 2026, 4:10 p.m.