Triple
T6906824
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | James Gambier, 1st Baron Gambier |
E159832
|
entity |
| Predicate | courtMartial |
P55751
|
FINISHED |
| Object | Basque Roads action |
—
|
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: Basque Roads action | Statement: [James Gambier, 1st Baron Gambier, courtMartial, Basque Roads action]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: courtMartial Context triple: [James Gambier, 1st Baron Gambier, courtMartial, Basque Roads action]
-
A.
courtMartialed
chosen
Indicates that a person has been subjected to a formal military trial for alleged violations of military law.
-
B.
courtroom
Indicates a relationship where a legal proceeding or judicial action takes place within or is associated with a specific courtroom.
-
C.
heldCourtUnder
Indicates that one authority conducted judicial or ceremonial court proceedings under the jurisdiction, auspices, or authority of another.
-
D.
courtMaterial
Indicates that one entity is the legal or judicial material, record, or document associated with a particular court or court proceeding.
-
E.
courtOfficial
Indicates that an entity serves in an official capacity within a court, holding an authorized role in judicial or legal proceedings.
- 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_69c68839ccb88190b4aa5cc1aca3448f |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6d98c3ab08190a1830c45578056ac |
completed | March 27, 2026, 7:25 p.m. |
| PD | Predicate disambiguation | batch_69c6d7b7681481909ec50509b19fcf81 |
completed | March 27, 2026, 7:17 p.m. |
Created at: March 27, 2026, 2:25 p.m.