Triple
T37536228
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Augustus C. Ludlow |
E933203
|
entity |
| Predicate | opposingShipInBattle |
P119410
|
FINISHED |
| Object | HMS Shannon |
—
|
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: HMS Shannon | Statement: [Augustus C. Ludlow, opposingShipInBattle, HMS Shannon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: opposingShipInBattle Context triple: [Augustus C. Ludlow, opposingShipInBattle, HMS Shannon]
-
A.
engagedEnemyShips
Indicates that one or more entities have actively attacked, exchanged fire with, or otherwise entered into direct combat with enemy ships.
-
B.
opponentShipClass
Indicates that one entity is the ship class of an opposing or enemy vessel relative to another entity.
-
C.
opponentFleet
Indicates that one fleet is in an adversarial or opposing relationship to another fleet.
-
D.
finalEngagementOpponentShip
chosen
Indicates that a ship is the opposing vessel faced in the final engagement or battle.
-
E.
capturedShip
Indicates that one party has taken control of another party's ship, typically by force or seizure.
- 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_69f76ec999288190ae26ec7b6aea7046 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fd8ccbd4c88190b13aae0673b3c821 |
completed | May 8, 2026, 7:12 a.m. |
| PD | Predicate disambiguation | batch_69fd8ae2227c819089546f5c3629799e |
completed | May 8, 2026, 7:04 a.m. |
Created at: May 3, 2026, 4:17 p.m.