Triple
T351826
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of the Coral Sea |
E7458
|
entity |
| Predicate | aircraftLostByAllies |
P12129
|
FINISHED |
| Object | approximately 69 aircraft |
—
|
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: approximately 69 aircraft | Statement: [Battle of the Coral Sea, aircraftLostByAllies, approximately 69 aircraft]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: aircraftLostByAllies Context triple: [Battle of the Coral Sea, aircraftLostByAllies, approximately 69 aircraft]
-
A.
aircraftLostByUnitedStates
Indicates that an aircraft was lost (e.g., destroyed, missing, or otherwise no longer operational) and that this loss is attributed to the United States.
-
B.
aircraftLostByJapan
Indicates that the specified aircraft were lost by Japan, typically through destruction, damage beyond repair, or disappearance.
-
C.
aircraftAlliedApprox
Indicates that one aircraft is approximately allied with another, reflecting a likely but not definitively confirmed friendly relationship between them.
-
D.
aircraftDestroyedUS
Indicates that a U.S. aircraft has been destroyed.
-
E.
aircraftDamagedUS
Indicates that a U.S. aircraft has been damaged, typically as a result of a specific event or action.
- 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_69a2e7e696948190bebc966535995e45 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2eb7f1be88190964ddcbb6a05f021 |
completed | Feb. 28, 2026, 1:19 p.m. |
| PD | Predicate disambiguation | batch_69a2e9571bd88190b6fcb16f21604720 |
completed | Feb. 28, 2026, 1:10 p.m. |
| PDg | Predicate description generation | batch_69a2ea0a4c448190a8a179daa9b90645 |
completed | Feb. 28, 2026, 1:13 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.