Triple
T7555774
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Army Nurse Corps |
E178661
|
entity |
| Predicate | historicalGenderPolicy |
P277
|
FINISHED |
| Object | originally restricted to women |
—
|
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: originally restricted to women | Statement: [Army Nurse Corps, historicalGenderPolicy, originally restricted to women]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: historicalGenderPolicy Context triple: [Army Nurse Corps, historicalGenderPolicy, originally restricted to women]
-
A.
hasGenderHistory
Indicates that an entity has undergone or experienced a change or transition in gender over time.
-
B.
hasGenderPolicy
chosen
Indicates that an entity has adopted, implemented, or is governed by a specific policy related to gender issues or gender equality.
-
C.
historicalLanguagePolicy
Indicates a relationship where an authority’s past rules or practices governed the use, status, or regulation of a language within a society or institution.
-
D.
governsGender
Indicates that one entity determines or constrains the gender classification or gender-related properties of another entity.
-
E.
formerGenderAdmission
Indicates that an institution previously admitted a particular gender but no longer does so.
- 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_69c69f2da22c8190a50942ac20af70e8 |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f8d82dd481908351876edc70c4ec |
completed | March 27, 2026, 9:38 p.m. |
| PD | Predicate disambiguation | batch_69c6f4dc485c819080da13e3b7f4f08f |
completed | March 27, 2026, 9:21 p.m. |
Created at: March 27, 2026, 3:49 p.m.