Triple

T4050928
Position Surface form Disambiguated ID Type / Status
Subject Gilead Sciences E84182 entity
Predicate product P490 FINISHED
Object Descovy
Descovy is a prescription antiretroviral medication from Gilead Sciences used for the treatment and prevention (PrEP) of HIV-1 infection.
 E409695 NE FINISHED

How this triple was built (4 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: Descovy | Statement: [Gilead Sciences, product, Descovy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Descovy
Context triple: [Gilead Sciences, product, Descovy]
  • A. Waylivra
    Waylivra is a prescription antisense oligonucleotide therapy used to treat familial chylomicronemia syndrome (FCS) by reducing triglyceride levels in the blood.
  • B. Darzalex
    Darzalex is a monoclonal antibody drug (daratumumab) used primarily in the treatment of multiple myeloma.
  • C. Anpezan
    Anpezan is a regional dialect of the Ladin language spoken in parts of the Dolomite area of northern Italy.
  • D. Denesuline
    Denesuline are a First Nations people of the larger Dene cultural and linguistic group, traditionally inhabiting subarctic regions of northern Canada.
  • E. Novafora
    Novafora was a semiconductor company known for acquiring Transmeta to expand its presence in low-power microprocessor and video processing technologies.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Descovy
Triple: [Gilead Sciences, product, Descovy]
Generated description
Descovy is a prescription antiretroviral medication from Gilead Sciences used for the treatment and prevention (PrEP) of HIV-1 infection.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Descovy
Target entity description: Descovy is a prescription antiretroviral medication from Gilead Sciences used for the treatment and prevention (PrEP) of HIV-1 infection.
  • A. Waylivra
    Waylivra is a prescription antisense oligonucleotide therapy used to treat familial chylomicronemia syndrome (FCS) by reducing triglyceride levels in the blood.
  • B. Darzalex
    Darzalex is a monoclonal antibody drug (daratumumab) used primarily in the treatment of multiple myeloma.
  • C. Anpezan
    Anpezan is a regional dialect of the Ladin language spoken in parts of the Dolomite area of northern Italy.
  • D. Denesuline
    Denesuline are a First Nations people of the larger Dene cultural and linguistic group, traditionally inhabiting subarctic regions of northern Canada.
  • E. Novafora
    Novafora was a semiconductor company known for acquiring Transmeta to expand its presence in low-power microprocessor and video processing technologies.
  • F. None of above. chosen

Provenance (5 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_69aed930bd5c819083e7dcc14fc44f69 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefb8539148190990468c1429be9dd completed March 9, 2026, 4:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69b55659256081909154569cedd1694a completed March 14, 2026, 12:36 p.m.
NEDg Description generation batch_69b5572b27c48190989311cef00b5f44 completed March 14, 2026, 12:40 p.m.
NED2 Entity disambiguation (via description) batch_69b55b333ffc8190a5df8b8d7bffa77f completed March 14, 2026, 12:57 p.m.
Created at: March 9, 2026, 3:37 p.m.