Triple
T35251386
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duke of Terceira |
E1018100
|
entity |
| Predicate | notableHolderMilitaryBranch |
P253
|
FINISHED |
| Object | Portuguese Army |
E40714
|
NE 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: Portuguese Army | Statement: [Duke of Terceira, notableHolderMilitaryBranch, Portuguese Army]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableHolderMilitaryBranch Context triple: [Duke of Terceira, notableHolderMilitaryBranch, Portuguese Army]
-
A.
hasMilitaryBranch
chosen
Indicates that an entity is associated with, served in, or is part of a specific branch of a military organization.
-
B.
namedForPersonMilitaryBranch
Indicates that a military branch is named in honor of or after a specific person.
-
C.
militaryBranchAssociatedWith
Indicates a relationship where an entity is connected to, or operates as part of, a specific branch of a military organization.
-
D.
militaryBranchDomain
Indicates that one entity serves as the military branch or armed forces component associated with the domain, jurisdiction, or organizational scope of another entity.
-
E.
militaryBranchOfGovernment
Indicates that a military organization functions as an official branch or component of a government.
- F. None of above.
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_69f76de407d081909dfc3c419817ae93 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a037c8c34f88190ace26f555827f23e |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a380fabab5881909e90bb150976c5e3 |
completed | June 21, 2026, 4:22 p.m. |
| PD | Predicate disambiguation | batch_6a037a016960819093ed4990fb4d9d36 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:02 p.m.