Triple
T32195940
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | phenytoin |
E822404
|
entity |
| Predicate | hasUNIID |
P37858
|
FINISHED |
| Object | 6158TKW0C5 |
—
|
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: 6158TKW0C5 | Statement: [phenytoin, hasUNIID, 6158TKW0C5]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasUNIID Context triple: [phenytoin, hasUNIID, 6158TKW0C5]
-
A.
hasUNII
chosen
Indicates that one entity is associated with a specific Unique Ingredient Identifier (UNII) code assigned by regulatory authorities.
-
B.
hasUNCode
Indicates that an entity is associated with a specific United Nations–assigned code that identifies it in UN systems or classifications.
-
C.
hasUnitIn
Indicates that one entity is contained or measured within another as a unit, specifying a unit-of-measure or component relationship.
-
D.
hasUnitNumber
Indicates that an entity is associated with a specific unit identifier or number within a larger building, complex, or organizational structure.
-
E.
hasURN
Indicates that an entity is associated with a specific Uniform Resource Name (URN) that uniquely identifies 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_69f3490819cc81909bae1f8ce99423c5 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f7be53890081909b1d93f30a8f31c6 |
completed | May 3, 2026, 9:29 p.m. |
| PD | Predicate disambiguation | batch_69f7bccacbac8190978976324c67db28 |
completed | May 3, 2026, 9:23 p.m. |
Created at: May 1, 2026, 12:35 a.m.