Triple

T6004956
Position Surface form Disambiguated ID Type / Status
Subject FUS E133686 entity
Predicate fullName P16 FINISHED
Object fused in sarcoma E133686 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: fused in sarcoma | Statement: [FUS, fullName, fused in sarcoma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: fused in sarcoma
Context triple: [FUS, fullName, fused in sarcoma]
  • A. Hodgkin
    Hodgkin is a surname most famously associated with Dorothy Hodgkin, the Nobel Prize–winning British chemist who advanced the field of X-ray crystallography.
  • B. Codman
    Codman is a surname most notably associated with Ogden Codman Jr., an influential American architect and interior decorator of the late 19th and early 20th centuries.
  • C. FUS chosen
    FUS is a DNA/RNA-binding protein whose mutations are implicated in neurodegenerative diseases, particularly certain forms of amyotrophic lateral sclerosis (ALS).
  • D. VHL
    VHL is the commonly used abbreviation for the Supreme Hockey League, a professional ice hockey league that operates primarily in Russia and surrounding countries.
  • E. non-Hodgkin lymphoma
    Non-Hodgkin lymphoma is a diverse group of blood cancers that originate in the lymphatic system from abnormal lymphocytes and can vary widely in aggressiveness and prognosis.
  • 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_69c00872444c8190bfaf1739dcec765c completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c04f10d18081908c351170b7f58d3d completed March 22, 2026, 8:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69c1088f5c84819094e4696c24c4dd79 completed March 23, 2026, 9:31 a.m.
Created at: March 22, 2026, 4:06 p.m.