Triple
T11297953
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Offspring Cohort |
E267501
|
entity |
| Predicate | studyDesign |
P98380
|
FINISHED |
| Object | prospective cohort study |
—
|
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: prospective cohort study | Statement: [Offspring Cohort, studyDesign, prospective cohort study]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: studyDesign Context triple: [Offspring Cohort, studyDesign, prospective cohort study]
-
A.
trialDesign
Indicates the specific structure, methodology, and procedural plan according to which a trial or experiment is conducted.
-
B.
studiesConcept
Indicates that an entity engages in learning, examining, or researching a particular concept.
-
C.
trialCharacterization
Indicates the specific features, conditions, or parameters that define and distinguish a particular trial within an experimental or procedural context.
-
D.
studiesProcess
Indicates that an entity systematically examines, researches, or learns about a particular process.
-
E.
conditionStudied
Indicates that a particular condition (e.g., disease, state, or circumstance) is the focus of study or investigation in a given context.
- F. None of above. chosen
Provenance (4 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_69d6aac993a08190a6f36445ebaf9a43 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e9a3616c8190a8fd23ca67463806 |
completed | April 9, 2026, 6:02 p.m. |
| PD | Predicate disambiguation | batch_69d787a6ca2c8190afdc24b61ccd3f8a |
completed | April 9, 2026, 11:04 a.m. |
| PDg | Predicate description generation | batch_69d796d049e88190a9fd7508f477f541 |
completed | April 9, 2026, 12:08 p.m. |
Created at: April 8, 2026, 9:32 p.m.