Triple
T13343140
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dr. Thorkel |
E317876
|
entity |
| Predicate | usesForExperiments |
P24615
|
FINISHED |
| Object | shrunken humans |
—
|
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: shrunken humans | Statement: [Dr. Thorkel, usesForExperiments, shrunken humans]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesForExperiments Context triple: [Dr. Thorkel, usesForExperiments, shrunken humans]
-
A.
includesExperiment
Indicates that one entity contains or encompasses a specific experiment as part of its scope, composition, or content.
-
B.
experimentedOn
Indicates that one entity conducted experiments or tests on another entity as the subject of investigation.
-
C.
supportsExperiment
Indicates that one entity provides the necessary resources, conditions, or assistance for an experiment to be conducted or to function as intended.
-
D.
hasResearchUse
chosen
Indicates that an entity is used for, or associated with, conducting research activities or purposes.
-
E.
hasTypeOfExperiment
Indicates that an experiment is associated with or classified under a specific type or category of experiment.
- 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_69d806b5a3c08190b42c267fb092f98a |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d99e8839b48190b164414b418e756c |
completed | April 11, 2026, 1:06 a.m. |
| PD | Predicate disambiguation | batch_69d98f6e53d88190bd6aa42f69b10ffb |
completed | April 11, 2026, 12:01 a.m. |
Created at: April 9, 2026, 9:31 p.m.