Triple
T30087199
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | optic tract |
E764630
|
entity |
| Predicate | containsFibersFrom |
P50523
|
FINISHED |
| Object | ipsilateral temporal retina |
—
|
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: ipsilateral temporal retina | Statement: [optic tract, containsFibersFrom, ipsilateral temporal retina]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: containsFibersFrom Context triple: [optic tract, containsFibersFrom, ipsilateral temporal retina]
-
A.
hasFiber
Indicates that one entity contains, includes, or is characterized by a certain amount or type of fiber.
-
B.
isFiberFed
chosen
Indicates that an entity receives or is supplied with fiber as its input or source.
-
C.
hasTypicalFiber
Indicates that an entity is characteristically associated with a particular type or kind of fiber.
-
D.
hasFiberDescribedAs
Indicates that an entity possesses dietary fiber characterized or specified by a particular description.
-
E.
hasFiberContent
Indicates that one entity contains a specified amount or level of dietary fiber.
- 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_69f22473c0fc8190a926a8051b3b378b |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69fed357b2b4819084c709056a54461f |
completed | May 9, 2026, 6:25 a.m. |
| PD | Predicate disambiguation | batch_69fed103d9cc81909b11619745110c61 |
completed | May 9, 2026, 6:15 a.m. |
Created at: April 29, 2026, 7:04 p.m.