Triple
T17241938
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ta 154 night fighter |
E418519
|
entity |
| Predicate | intendedOpponent |
P89124
|
FINISHED |
| Object | Allied heavy bombers |
—
|
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: Allied heavy bombers | Statement: [Ta 154 night fighter, intendedOpponent, Allied heavy bombers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: intendedOpponent Context triple: [Ta 154 night fighter, intendedOpponent, Allied heavy bombers]
-
A.
intendedOpponents
chosen
Indicates that one entity is the target or adversary that another entity is meant or designed to oppose or confront.
-
B.
battleOpponent
Indicates that two entities are engaged in or designated as opponents in a battle or combat scenario.
-
C.
facedOpponent
Indicates that one entity directly confronted or competed against another as an opponent in a contest, conflict, or challenge.
-
D.
decidingOpponent
Indicates that one entity is the opponent or counterpart responsible for making a decision that affects another entity.
-
E.
laterOpponent
Indicates that one entity becomes the opponent of another at a later time or stage, following an earlier phase or matchup.
- 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_69d886d8e96081909870bff6c3d0bf09 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42e21003c81908c884a3c8712676a |
completed | April 19, 2026, 1:21 a.m. |
| PD | Predicate disambiguation | batch_69e3832553ac819091aa917c84f755b6 |
completed | April 18, 2026, 1:12 p.m. |
Created at: April 10, 2026, 5:39 a.m.