Triple
T17035770
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stray |
E413316
|
entity |
| Predicate | B-12Function |
P70740
|
FINISHED |
| Object | translation |
—
|
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: translation | Statement: [Stray, B-12Function, translation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: B-12Function Context triple: [Stray, B-12Function, translation]
-
A.
B_12
chosen
Indicates that one entity is associated with vitamin B12, such as containing, providing, or being characterized by it.
-
B.
B_6
Indicates that one entity is the biological sibling of another, specifically the sixth such sibling in an ordered set or sequence.
-
C.
containsBGroupVitamins
Indicates that one entity includes or has B-group vitamins as part of its composition.
-
D.
hasBioavailability
Indicates that a substance has a specified degree or measure of bioavailability, i.e., the proportion that enters circulation and can have an active effect.
-
E.
providesFunctionalityOf
Indicates that one entity supplies, implements, or makes available the capabilities or functions that are normally associated with another entity.
- 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_69d886cd18288190b006abab23f811b7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d8f26f50819085dfd0fbecd6394d |
completed | April 18, 2026, 7:18 p.m. |
| PD | Predicate disambiguation | batch_69e35d5be7f48190af9db67a1e23850f |
completed | April 18, 2026, 10:30 a.m. |
Created at: April 10, 2026, 5:33 a.m.