Triple
T36720146
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Katherine Duer Mackay |
E907032
|
entity |
| Predicate | typeOfSocialite |
P94712
|
FINISHED |
| Object | New York socialite |
—
|
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: New York socialite | Statement: [Katherine Duer Mackay, typeOfSocialite, New York socialite]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfSocialite Context triple: [Katherine Duer Mackay, typeOfSocialite, New York socialite]
-
A.
socialType
Indicates the category or nature of a social relationship or interaction that exists between entities.
-
B.
protagonistSocialType
Indicates the type of social role, status, or interaction style that the protagonist has within the context of the narrative or scenario.
-
C.
portraysSocialTypes
Indicates that an entity depicts or represents particular social roles, groups, or character types.
-
D.
profileType
Indicates the specific category or role classification assigned to a profile within a system.
-
E.
personType
chosen
Indicates that an entity is classified as a particular type or category of person.
- 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_69f76e746e4c8190a0d05cc6d57a643e |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a0324c2d618819093f7e6424b0f5baf |
completed | May 12, 2026, 1:01 p.m. |
| PD | Predicate disambiguation | batch_6a0324292e588190b37d0c3016ea2062 |
completed | May 12, 2026, 12:59 p.m. |
Created at: May 3, 2026, 4:12 p.m.