Triple
T26812434
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dukes of the Infantado |
E672031
|
entity |
| Predicate | heldPositions |
P8
|
FINISHED |
| Object | military commanders |
—
|
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: military commanders | Statement: [Dukes of the Infantado, heldPositions, military commanders]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heldPositions Context triple: [Dukes of the Infantado, heldPositions, military commanders]
-
A.
positionHeld
chosen
Indicates that an entity occupies or has occupied a specific role, job, office, or position within an organization or context.
-
B.
positionHeldUnder
Indicates that one entity holds or held a specific position, office, or role under the authority, administration, or jurisdiction of another entity.
-
C.
canAlsoHoldPosition
Indicates that an entity, in addition to its current role or position, is capable of occupying or being assigned another specified position.
-
D.
holdingOf
Indicates that one entity is in possession of, or physically grasping, another entity.
-
E.
held
Indicates that one entity physically grasped, carried, or kept another entity in its possession 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_69eeb3225a3c8190aaf6746efeded2f3 |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f61a830edc8190a73ebf0085d5d151 |
completed | May 2, 2026, 3:38 p.m. |
| PD | Predicate disambiguation | batch_69f611ad2eb48190ac1ed0090f13f7a9 |
completed | May 2, 2026, 3:01 p.m. |
Created at: April 27, 2026, 4:30 a.m.