Triple
T15864395
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Admiral Scheer |
E384671
|
entity |
| Predicate | resultOfConvoyHX84Attack |
P19109
|
FINISHED |
| Object | several merchant ships sunk |
—
|
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: several merchant ships sunk | Statement: [Admiral Scheer, resultOfConvoyHX84Attack, several merchant ships sunk]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: resultOfConvoyHX84Attack Context triple: [Admiral Scheer, resultOfConvoyHX84Attack, several merchant ships sunk]
-
A.
resultOfSecondAttack
Indicates that an event or state occurs as a consequence of a second attack in a sequence of attacks.
-
B.
resultOfSiege
Indicates that one entity is the outcome or consequence produced by a siege conducted against another entity.
-
C.
convoyProtected
Indicates that one entity provides protective escort or defense to a moving group (convoy) of other entities during transit.
-
D.
resultOfBattle
chosen
Indicates that one entity is the outcome or consequence produced by a specific battle or combat event involving another entity.
-
E.
tacticalOutcome
Indicates the specific result or consequence produced by a particular tactic or tactical action in a given situation.
- 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_69d86da4e86481909f1325fdc971b5ec |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e174de2cd48190ab18e48c9f051a2a |
completed | April 16, 2026, 11:46 p.m. |
| PD | Predicate disambiguation | batch_69e142b976c081908d3ba3e705419f3a |
completed | April 16, 2026, 8:12 p.m. |
Created at: April 10, 2026, 4:50 a.m.