Triple

T363288
Position Surface form Disambiguated ID Type / Status
Subject Genentech E7901 entity
Predicate notableProduct P1448 FINISHED
Object Perjeta
Perjeta is a monoclonal antibody drug used in combination therapies to treat HER2-positive breast cancer.
 E46091 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: Perjeta | Statement: [Genentech, notableProduct, Perjeta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Perjeta
Context triple: [Genentech, notableProduct, Perjeta]
  • A. Leto
    Leto is a Titaness in Greek mythology best known as the mother of the twin Olympian deities Apollo and Artemis.
  • B. Day
    "Day" is a memoir by Elie Wiesel that continues his reflection on Holocaust survival and its psychological aftermath, following the events depicted in "Night."
  • C. Madruga
    Madruga is a municipality in western Cuba known for its rural character and location within the historical region surrounding Havana.
  • D. Juché
    Juché is an alternative spelling of Juche, the North Korean state ideology centered on self-reliance and the absolute leadership of the Kim dynasty.
  • E. Brega
    Brega is a strategic coastal town in northeastern Libya known for its major oil facilities and its role as a key battleground during the 2011 Libyan Civil War.
  • 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: Perjeta
Triple: [Genentech, notableProduct, Perjeta]
Generated description
Perjeta is a monoclonal antibody drug used in combination therapies to treat HER2-positive breast cancer.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Perjeta
Target entity description: Perjeta is a monoclonal antibody drug used in combination therapies to treat HER2-positive breast cancer.
  • A. Leto
    Leto is a Titaness in Greek mythology best known as the mother of the twin Olympian deities Apollo and Artemis.
  • B. Day
    "Day" is a memoir by Elie Wiesel that continues his reflection on Holocaust survival and its psychological aftermath, following the events depicted in "Night."
  • C. Madruga
    Madruga is a municipality in western Cuba known for its rural character and location within the historical region surrounding Havana.
  • D. Juché
    Juché is an alternative spelling of Juche, the North Korean state ideology centered on self-reliance and the absolute leadership of the Kim dynasty.
  • E. Brega
    Brega is a strategic coastal town in northeastern Libya known for its major oil facilities and its role as a key battleground during the 2011 Libyan Civil War.
  • 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_69a2e7e880008190a6ad7e06e5d03007 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2ebd1016481909b8ba3b047a47145 completed Feb. 28, 2026, 1:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69a3e86533a481909bab5f0b52114c6a completed March 1, 2026, 7:19 a.m.
NEDg Description generation batch_69a3e99fd210819099e83cd183a4daa7 completed March 1, 2026, 7:24 a.m.
NED2 Entity disambiguation (via description) batch_69a3ea45c86c8190a6c215430601ad15 completed March 1, 2026, 7:27 a.m.
Created at: Feb. 28, 2026, 1:08 p.m.