Triple
T26912893
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ann Demeulemeester |
E677436
|
entity |
| Predicate | cohort |
P98382
|
FINISHED |
| Object | Marina Yee |
—
|
NE NERFINISHED |
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: Marina Yee | Statement: [Ann Demeulemeester, cohort, Marina Yee]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cohort Context triple: [Ann Demeulemeester, cohort, Marina Yee]
-
A.
cohortBased
Indicates that entities are grouped or treated together based on belonging to the same cohort (e.g., time-based or batch-based grouping).
-
B.
cohortStructure
Indicates the organizational relationship that defines how a cohort is structured or grouped into its constituent parts.
-
C.
relatedCohort
chosen
Indicates that two or more entities are associated through membership in, or connection to, the same cohort or grouped population.
-
D.
numberOfCohorts
Indicates the total count of distinct cohorts associated with or involved in a given entity or context.
-
E.
supercohort
Indicates a relationship where one cohort encompasses, aggregates, or is hierarchically above one or more other cohorts within a grouping or classification structure.
- 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_69eee9bcef1c8190be88586bb902bb9b |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69f62d53ad58819080c5227c7a729d15 |
completed | May 2, 2026, 4:58 p.m. |
| PD | Predicate disambiguation | batch_69f62c15952881908a5ea0c25904afec |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 6:02 a.m.