Triple
T18021068
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Purkinje fibers |
E431116
|
entity |
| Predicate | stainCharacteristic |
P99727
|
FINISHED |
| Object | PAS positive due to glycogen |
—
|
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: PAS positive due to glycogen | Statement: [Purkinje fibers, stainCharacteristic, PAS positive due to glycogen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stainCharacteristic Context triple: [Purkinje fibers, stainCharacteristic, PAS positive due to glycogen]
-
A.
spanCharacteristic
Indicates that one entity has a particular measurable or descriptive property that characterizes the extent, duration, or range of another entity or phenomenon.
-
B.
stainingProperty
chosen
Indicates a relationship where one entity has a particular staining behavior or characteristic when subjected to a specific stain or staining method.
-
C.
stainLocation
Indicates the specific place or area where a stain is present or occurs.
-
D.
stainMethod
Indicates the technique or procedure used to apply a stain to a material or specimen.
-
E.
catalogCharacteristic
Indicates that a catalog has a specific characteristic or attribute associated with it.
- 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_69d8b904530081908bf341d842464856 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4b9c299c48190b0cceecf77cb6de9 |
completed | April 19, 2026, 11:17 a.m. |
| PD | Predicate disambiguation | batch_69e3f904b8048190add43883cd7cb191 |
completed | April 18, 2026, 9:35 p.m. |
Created at: April 10, 2026, 10:24 a.m.