Triple
T27853803
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Batalla de Las Piedras |
E704029
|
entity |
| Predicate | comandanteDelBando2 |
P68449
|
FINISHED |
| Object | José de Posadas |
—
|
NE NERFINISHED |
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: José de Posadas | Statement: [Batalla de Las Piedras, comandanteDelBando2, José de Posadas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: comandanteDelBando2 Context triple: [Batalla de Las Piedras, comandanteDelBando2, José de Posadas]
-
A.
battleCommanderMexican
Indicates that one entity serves as the Mexican commander or leading military officer in a particular battle involving the other entity.
-
B.
hadSecondInCommand
Indicates that one entity had another entity serving as its second-in-command or primary subordinate leader.
-
C.
sideCommander
chosen
Indicates that an entity serves as the commanding officer or leader in charge of a particular side or faction in a conflict, operation, or organization.
-
D.
commanderForSpain
Indicates that a person serves or has served as a military commander on behalf of Spain.
-
E.
capturedCommander
Indicates that one party has taken a military commander from another party into custody or control.
- 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_69ef840e614c8190a88cf9638c14a265 |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_69f63b317e048190963989b732b25b91 |
completed | May 2, 2026, 5:58 p.m. |
| PD | Predicate disambiguation | batch_69f6370ea79c81909b761821ee0fa698 |
completed | May 2, 2026, 5:40 p.m. |
Created at: April 27, 2026, 6:12 p.m.