Triple
T21060165
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marshal of the Korean People's Army |
E518827
|
entity |
| Predicate | hasGenderApplicability |
P15554
|
FINISHED |
| Object | can be held by men |
—
|
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: can be held by men | Statement: [Marshal of the Korean People's Army, hasGenderApplicability, can be held by men]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGenderApplicability Context triple: [Marshal of the Korean People's Army, hasGenderApplicability, can be held by men]
-
A.
hasGenderNeutralEligibility
Indicates that an entity is eligible or applicable in a way that does not depend on or specify a particular gender.
-
B.
usedByGender
Indicates that something is utilized, applied, or engaged in by entities of a specified gender.
-
C.
hasGenderRequirement
chosen
Indicates that a particular role, activity, or context specifies a required or restricted gender for participation or eligibility.
-
D.
hasGenderVariant
Indicates that one entity is a gender-specific form or variant of another entity.
-
E.
hasGenderInterpretation
Indicates that an entity is associated with a particular interpretation or understanding of gender.
- 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_69e0b505ef108190b25dd4033e2ff7eb |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fd842e8881909f4ffc4c43b7fa9f |
completed | April 21, 2026, 4:31 a.m. |
| PD | Predicate disambiguation | batch_69e5dbf9d71881908cd85dfc37db93ca |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 16, 2026, 2:37 p.m.