Triple
T8902193
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | thalamus |
E211955
|
entity |
| Predicate | locatedMedialTo |
P86292
|
FINISHED |
| Object | internal capsule |
—
|
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: internal capsule | Statement: [thalamus, locatedMedialTo, internal capsule]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedMedialTo Context triple: [thalamus, locatedMedialTo, internal capsule]
-
A.
locatedBetween
Indicates that one entity is positioned spatially between two other reference entities.
-
B.
locatedAfter
Indicates that one entity is positioned later than another along a defined sequence, order, or spatial/temporal axis.
-
C.
locatedInOrAdjacentTo
Indicates that one entity is either situated within the boundaries of another entity or directly next to it, sharing a common border or edge.
-
D.
locatedOnBody
Indicates that one entity is physically situated on the surface or external part of another entity’s body.
-
E.
locatedBehind
Indicates that one entity is positioned at the rear of or on the far side of another entity along a given viewing or reference direction.
- 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_69ca83918d3081909b326fa3750cb8c8 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc642a104081908df2d64e8f9ad0c8 |
completed | April 1, 2026, 12:17 a.m. |
| PD | Predicate disambiguation | batch_69cc5ecf55248190a29f00fbf99f13c4 |
completed | March 31, 2026, 11:54 p.m. |
| PDg | Predicate description generation | batch_69cc604965c48190bbb6db0ae8108e67 |
completed | April 1, 2026, 12:01 a.m. |
Created at: March 30, 2026, 6:55 p.m.