Triple

T15983056
Position Surface form Disambiguated ID Type / Status
Subject Juno Therapeutics E387620 entity
Predicate productCandidate P64697 FINISHED
Object JCAR015
JCAR015 is an investigational CAR T-cell therapy developed by Juno Therapeutics for the treatment of certain blood cancers, particularly acute lymphoblastic leukemia.
E1189577 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: JCAR015 | Statement: [Juno Therapeutics, productCandidate, JCAR015]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: JCAR015
Context triple: [Juno Therapeutics, productCandidate, JCAR015]
  • A. JCAR017
    JCAR017 is an investigational CAR T-cell therapy developed by Juno Therapeutics for the treatment of certain blood cancers.
  • B. J150
    J150 is the fifth-generation Toyota Land Cruiser Prado series, a mid-size SUV platform known for its off-road capability and global popularity.
  • C. CJC
    CJC is the IATA airport code for El Loa Airport serving the city of Calama in northern Chile.
  • D. CJC
    CJC is the commonly used abbreviation for the College of Journalism and Communications, an academic institution focused on media, journalism, and communication studies.
  • E. J1
    J1 is the top professional football (soccer) division in Japan, featuring the country’s highest-level clubs.
  • 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: JCAR015
Triple: [Juno Therapeutics, productCandidate, JCAR015]
Generated description
JCAR015 is an investigational CAR T-cell therapy developed by Juno Therapeutics for the treatment of certain blood cancers, particularly acute lymphoblastic leukemia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: JCAR015
Target entity description: JCAR015 is an investigational CAR T-cell therapy developed by Juno Therapeutics for the treatment of certain blood cancers, particularly acute lymphoblastic leukemia.
  • A. JCAR017
    JCAR017 is an investigational CAR T-cell therapy developed by Juno Therapeutics for the treatment of certain blood cancers.
  • B. J150
    J150 is the fifth-generation Toyota Land Cruiser Prado series, a mid-size SUV platform known for its off-road capability and global popularity.
  • C. CJC
    CJC is the IATA airport code for El Loa Airport serving the city of Calama in northern Chile.
  • D. CJC
    CJC is the commonly used abbreviation for the College of Journalism and Communications, an academic institution focused on media, journalism, and communication studies.
  • E. J1
    J1 is the top professional football (soccer) division in Japan, featuring the country’s highest-level clubs.
  • 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_69d86da94ccc819083d187f5dc6a123e completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1828e9e708190aec0078913bf098a completed April 17, 2026, 12:45 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffcf1abad48190a42510605c30d0b3 completed May 10, 2026, 12:19 a.m.
NEDg Description generation batch_69ffd049952081909221df73d3555557 completed May 10, 2026, 12:24 a.m.
NED2 Entity disambiguation (via description) batch_69ffd10ab484819089cd94ef07cb8de5 completed May 10, 2026, 12:27 a.m.
Created at: April 10, 2026, 4:54 a.m.