Triple
T12948600
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SMS Scharnhorst |
E309830
|
entity |
| Predicate | resultAtBattleOfCoronel |
P107648
|
FINISHED |
| Object | German victory |
—
|
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: German victory | Statement: [SMS Scharnhorst, resultAtBattleOfCoronel, German victory]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: resultAtBattleOfCoronel Context triple: [SMS Scharnhorst, resultAtBattleOfCoronel, German victory]
-
A.
opponentInBattleOfTheRiverPlate
Indicates that two entities were opposing sides facing each other in the Battle of the River Plate.
-
B.
engagementOutcomeAtBattleOfIquique
Indicates the result or outcome of a specific party’s engagement in the Battle of Iquique.
-
C.
dateOfCommandAtBattleOfCoronel
Indicates the specific calendar date on which a command was held or exercised during the Battle of Coronel.
-
D.
commandingOfficerAtBattleOfIquique
Indicates that one entity served as the commanding officer of the other entity during the Battle of Iquique.
-
E.
roleAtBattleOfIquique
Indicates the specific role or function an entity held during the Battle of Iquique.
- 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_69d7bdfb57a88190836b743e2825feca |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d97e59a4c88190907d05b8d57dae89 |
completed | April 10, 2026, 10:48 p.m. |
| PD | Predicate disambiguation | batch_69d97db69f548190a1a693bc0d6c191a |
completed | April 10, 2026, 10:46 p.m. |
| PDg | Predicate description generation | batch_69d97e5811f481908178fac6d2e0efcd |
completed | April 10, 2026, 10:48 p.m. |
Created at: April 9, 2026, 5:43 p.m.