Triple
T37812187
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Courageous-class aircraft carrier |
E942675
|
entity |
| Predicate | notableLossCause |
P59430
|
FINISHED |
| Object | submarine attack |
—
|
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: submarine attack | Statement: [Courageous-class aircraft carrier, notableLossCause, submarine attack]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableLossCause Context triple: [Courageous-class aircraft carrier, notableLossCause, submarine attack]
-
A.
causedLossOf
chosen
Indicates that one entity brought about or was responsible for another entity experiencing a loss.
-
B.
reasonForContactLoss
Indicates the cause or circumstance that led to the loss or termination of contact between entities.
-
C.
managedLossesRecord
Indicates that an entity maintains or oversees a record documenting losses that have been managed or handled.
-
D.
notableProtectiveFailure
Indicates a relationship where an entity’s protective role or safeguards significantly failed, leading to a notable or consequential breakdown in protection.
-
E.
significantLoss
Indicates that an entity has experienced a major or substantial decrease in value, quantity, or status beyond a normal or minor loss.
- 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_69f76ee8104c8190ab17133ccd8f86e6 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a037c903be48190a2fafa53d7d50d42 |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a1772e48190ba738c6d11b321e2 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:19 p.m.