Triple

T2138516
Position Surface form Disambiguated ID Type / Status
Subject Roche E46707 entity
Predicate product P490 FINISHED
Object Perjeta E46091 NE 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: Perjeta | Statement: [Roche, product, Perjeta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Perjeta
Context triple: [Roche, product, Perjeta]
  • A. Perjeta chosen
    Perjeta is a monoclonal antibody drug used in combination therapies to treat HER2-positive breast cancer.
  • B. Mardi
    "Mardi" is an 1849 novel by Herman Melville, known as his first major foray into philosophical and allegorical fiction set in a fantastical South Seas archipelago.
  • C. Muanda
    Muanda is a coastal town in the Democratic Republic of the Congo situated near the mouth of the Congo River on the Atlantic Ocean.
  • D. Perka
    Perka is a small settlement located on Car Nicobar Island in the Nicobar district of India’s Andaman and Nicobar Islands.
  • E. Perdika
    Perdika is a small coastal village on the Greek island of Aegina, known for its traditional tavernas, fishing harbor, and views toward the islet of Moni.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69a88a174ab48190a5db20c132e5dccf completed March 4, 2026, 7:37 p.m.
NER Named-entity recognition batch_69abbe012aa481909ffa0a50e58efabb completed March 7, 2026, 5:56 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae51b1290c8190a08850b428c99a6c completed March 9, 2026, 4:50 a.m.
Created at: March 4, 2026, 7:44 p.m.