Triple
T21672097
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Cape St. Vincent (1780) |
E534873
|
entity |
| Predicate | commandRank (Juan de Lángara) |
P90400
|
FINISHED |
| Object | Admiral |
—
|
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: Admiral | Statement: [Battle of Cape St. Vincent (1780), commandRank (Juan de Lángara), Admiral]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: commandRank (Juan de Lángara) Context triple: [Battle of Cape St. Vincent (1780), commandRank (Juan de Lángara), Admiral]
-
A.
MexicanCommanderRank
Indicates that one entity holds a specific military commander rank within the Mexican armed forces in relation to another entity or context.
-
B.
commanderForSpain
Indicates that a person serves or has served as a military commander on behalf of Spain.
-
C.
hasCommanderRank
Indicates that an entity holds the military or organizational rank of commander within a specified hierarchy or context.
-
D.
rankOfNotableCommander
chosen
Indicates the military or organizational rank held by a notable commander associated with an entity.
-
E.
rankInSpanishHonoursSystem
Indicates the specific hierarchical position a person holds within the system of Spanish honors and decorations.
- 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_69e0c46898008190aa618a4af55bd1ee |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef8a0cd7648190b9981393f0b2bee9 |
completed | April 27, 2026, 4:08 p.m. |
| PD | Predicate disambiguation | batch_69e6968abfdc81909cf9e0bd72db9eca |
completed | April 20, 2026, 9:11 p.m. |
Created at: April 16, 2026, 6:39 p.m.