Triple
T27983738
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eau de Cologne |
E706690
|
entity |
| Predicate | typicalGenderMarketing |
P34349
|
FINISHED |
| Object | unisex |
—
|
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: unisex | Statement: [Eau de Cologne, typicalGenderMarketing, unisex]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalGenderMarketing Context triple: [Eau de Cologne, typicalGenderMarketing, unisex]
-
A.
genderTypically
Indicates that something is most commonly or traditionally associated with a particular gender.
-
B.
hasTypicalGenderAssociation
chosen
Indicates that one entity is commonly or culturally associated with a particular gender more than with other genders.
-
C.
genderTarget
Indicates that an action, message, or effect is specifically directed toward entities of a particular gender.
-
D.
sponsoredGender
Indicates that one entity provides financial or material sponsorship specifically related to the gender of another entity.
-
E.
usedByGender
Indicates that something is utilized, applied, or engaged in by entities of a specified 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_69ef96b8b8d88190bad5e4ae966bf14e |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_6a004d0b46148190bcec4ea67acfe170 |
completed | May 10, 2026, 9:16 a.m. |
| PD | Predicate disambiguation | batch_6a004c92283081909f229c1720af155a |
completed | May 10, 2026, 9:14 a.m. |
Created at: April 27, 2026, 7:46 p.m.