Triple
T8073035
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Scardina v. Masterpiece Cakeshop |
E188420
|
entity |
| Predicate | plaintiffGenderIdentity |
P43613
|
FINISHED |
| Object | transgender woman |
—
|
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: transgender woman | Statement: [Scardina v. Masterpiece Cakeshop, plaintiffGenderIdentity, transgender woman]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: plaintiffGenderIdentity Context triple: [Scardina v. Masterpiece Cakeshop, plaintiffGenderIdentity, transgender woman]
-
A.
hasGenderIdentity
chosen
Indicates that an entity identifies with or experiences a particular gender.
-
B.
protagonistGenderIdentity
Indicates the gender identity attributed to or expressed by the protagonist in a given context.
-
C.
genderVariant
Indicates that an entity’s gender identity or expression differs from traditional or expected norms associated with their assigned sex or gender.
-
D.
genderImplication
Indicates that one entity’s gender suggests, constrains, or determines the possible or likely gender of another entity.
-
E.
genderConfiguration
Indicates how the genders of the involved entities are arranged or combined within a particular relationship or context.
- 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_69ca82b50c708190863f661d438e68df |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb40482200819086c639f64c01fbb5 |
completed | March 31, 2026, 3:32 a.m. |
| PD | Predicate disambiguation | batch_69cb049f1614819087360d1a4c6f0faa |
completed | March 30, 2026, 11:17 p.m. |
Created at: March 30, 2026, 5:27 p.m.