Triple
T32279813
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | nivolumab |
E824658
|
entity |
| Predicate | combinationWith |
P131235
|
FINISHED |
| Object | ipilimumab |
—
|
NE NERFINISHED |
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: ipilimumab | Statement: [nivolumab, combinationWith, ipilimumab]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: combinationWith Context triple: [nivolumab, combinationWith, ipilimumab]
-
A.
combinationType
Indicates how multiple elements are combined or related to each other within a composite structure or operation.
-
B.
combinedIn
Indicates that two or more entities are merged, joined, or used together to form a single combined whole or context.
-
C.
typicalCombinationWith
chosen
Indicates that one entity is commonly or characteristically used, found, or occurs together in combination with another entity.
-
D.
laterCombination
Indicates that one entity is a combination or composite that occurs after, or is formed subsequent to, another entity or state.
-
E.
originalCombinationFor
Indicates that one entity is the initial or source combination from which another combined entity is derived or constructed.
- 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_69f3490f404081908450db66884f4334 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6bcc7edfc81909d0008fa9364de54 |
completed | May 3, 2026, 3:11 a.m. |
| PD | Predicate disambiguation | batch_69f6ba6cef208190bc5cd43d96127004 |
completed | May 3, 2026, 3:01 a.m. |
Created at: May 1, 2026, 12:43 a.m.