Triple
T19389194
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marjorie Harvey |
E485016
|
entity |
| Predicate | socialMediaPresenceIn |
P89371
|
FINISHED |
| Object | fashion content |
—
|
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: fashion content | Statement: [Marjorie Harvey, socialMediaPresenceIn, fashion content]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: socialMediaPresenceIn Context triple: [Marjorie Harvey, socialMediaPresenceIn, fashion content]
-
A.
socialMediaAppearance
chosen
Indicates that an entity is featured, mentioned, or otherwise present in a piece of content on a social media platform.
-
B.
socialMedia
Indicates a relationship where one entity uses, is associated with, or interacts through social networking or content-sharing platforms with another entity.
-
C.
socialMediaPlatformAssociatedWith
Indicates that there is an association or linkage between an entity and a specific social media platform.
-
D.
socialSphere
Indicates the social environment or network within which an entity regularly interacts or maintains relationships.
-
E.
socialProfile
Indicates that an entity has an associated social media or online networking profile.
- 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_69d8e8d460d88190abf0591c5c9d2b0c |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e61b4328448190b6347c41265e820c |
completed | April 20, 2026, 12:25 p.m. |
| PD | Predicate disambiguation | batch_69e4fd602f008190aa9bc76ae17e4ce1 |
completed | April 19, 2026, 4:05 p.m. |
Created at: April 10, 2026, 1:36 p.m.