Triple
T19157078
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MRK |
E468952
|
entity |
| Predicate | issuerMajorProductType |
P29435
|
FINISHED |
| Object | Cancer immunotherapy |
—
|
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: Cancer immunotherapy | Statement: [MRK, issuerMajorProductType, Cancer immunotherapy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: issuerMajorProductType Context triple: [MRK, issuerMajorProductType, Cancer immunotherapy]
-
A.
issuerType
Indicates the classification or category of the entity that issues something (such as a document, credential, or instrument).
-
B.
issuerBusinessType
Indicates the category or nature of business activity that the issuing entity is engaged in.
-
C.
issuerCustomerType
Indicates the type or category of customer associated with or defined by the issuer.
-
D.
issuerMainPlatform
Indicates that an entity serves as the primary platform or main environment through which an issuer operates, offers, or manages its services or instruments.
-
E.
issuerSpecialization
chosen
Indicates the particular field, domain, or area of expertise in which the issuer is specialized.
- 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_69d8dd084ff48190ac0f8c46ee722629 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5eeb9cf9081908b17073755e83554 |
completed | April 20, 2026, 9:15 a.m. |
| PD | Predicate disambiguation | batch_69e4b9b83d6881908e6271c620f74100 |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 12:06 p.m.