Triple
T7699980
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marie Pasteur |
E174465
|
entity |
| Predicate | supportedResearchIn |
P36686
|
FINISHED |
| Object | germ theory of disease |
—
|
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: germ theory of disease | Statement: [Marie Pasteur, supportedResearchIn, germ theory of disease]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportedResearchIn Context triple: [Marie Pasteur, supportedResearchIn, germ theory of disease]
-
A.
supportedResearch
Indicates that one entity provided assistance, resources, or backing to enable or advance the research activities of another entity.
-
B.
supportsResearchIn
chosen
Indicates that one entity provides resources, assistance, or infrastructure that enables or advances research activities in a particular field or area for another entity.
-
C.
researchSupportType
Indicates the specific kind of support provided for research activities, such as funding, resources, or services.
-
D.
usedResearchFrom
Indicates that one entity based its work, findings, or outputs on research conducted or provided by another entity.
-
E.
usesResearchSubject
Indicates that one entity employs or utilizes another entity as a research subject in a study or investigation.
- 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_69c6995a72cc8190998e56daa6f8e453 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c70402169481909b219dc5f4a64b9b |
completed | March 27, 2026, 10:26 p.m. |
| PD | Predicate disambiguation | batch_69c70165e78c8190bf6b3c34e243cb81 |
completed | March 27, 2026, 10:15 p.m. |
Created at: March 27, 2026, 4:03 p.m.