Triple
T37192597
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | When I Was a Girl I Used to Scream and Shout |
E921498
|
entity |
| Predicate | hasCastGenderFocus |
P2452
|
FINISHED |
| Object | primarily female characters |
—
|
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: primarily female characters | Statement: [When I Was a Girl I Used to Scream and Shout, hasCastGenderFocus, primarily female characters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCastGenderFocus Context triple: [When I Was a Girl I Used to Scream and Shout, hasCastGenderFocus, primarily female characters]
-
A.
hasGenderFocus
chosen
Indicates that something is specifically concerned with, oriented toward, or primarily addressing a particular gender or gender-related issues.
-
B.
hasLeadCharacterGender
Indicates that the primary or lead character in a work has a specified gender.
-
C.
hasGenderRole
Indicates that an entity is associated with, or expected to perform, a particular socially defined gender-based role or set of behaviors.
-
D.
hasDirectorGender
Indicates that an entity has a director whose gender is specified by the related value.
-
E.
hasPerformerGender
Indicates that an action, event, or performance is associated with the gender of the performer who carries it out.
- 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_69f76ea313a08190a54404cd1e47da90 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fff9b126b4819085a4cf8791d388d1 |
completed | May 10, 2026, 3:21 a.m. |
| PD | Predicate disambiguation | batch_69fff8f913a881908d3b7e490d92631f |
completed | May 10, 2026, 3:18 a.m. |
Created at: May 3, 2026, 4:15 p.m.