Triple
T34752507
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ticonderoga-class cruiser |
E1001819
|
entity |
| Predicate | laterFlightShips |
P201975
|
FINISHED |
| Object | CG-52 to CG-73 |
—
|
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: CG-52 to CG-73 | Statement: [Ticonderoga-class cruiser, laterFlightShips, CG-52 to CG-73]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterFlightShips Context triple: [Ticonderoga-class cruiser, laterFlightShips, CG-52 to CG-73]
-
A.
laterShipType
Indicates that one ship type chronologically succeeds or is introduced after another ship type.
-
B.
shipsWith
Indicates that one entity is delivered, packaged, or provided together with another entity as part of the same shipment or bundle.
-
C.
ferryFlightCarrier
Indicates that one carrier operates a ferry (non-revenue repositioning) flight on behalf of another carrier.
-
D.
boardsShip
Indicates that one entity gets onto or enters a ship as a passenger or crew member.
-
E.
plannedShip
Indicates that an entity is scheduled or intended to be shipped at a future time.
- 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_69f76db0fb30819096709d43f9a1f45f |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_6a003f6083608190a5deadc7291cf70e |
completed | May 10, 2026, 8:18 a.m. |
| PD | Predicate disambiguation | batch_6a003c935c40819085fdb255a52ba03b |
completed | May 10, 2026, 8:06 a.m. |
| PDg | Predicate description generation | batch_6a003f5fa0108190bea7f7b6b6ec6baf |
completed | May 10, 2026, 8:18 a.m. |
Created at: May 3, 2026, 3:59 p.m.