Triple

T22796872
Position Surface form Disambiguated ID Type / Status
Subject Gemin3 E564272 entity
Predicate hasAlternativeName P39 FINISHED
Object DEAD-box helicase 20 NE NERFINISHED

How this triple was built (3 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: DEAD-box helicase 20 | Statement: [Gemin3, hasAlternativeName, DEAD-box helicase 20]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: DEAD-box helicase 20
Context triple: [Gemin3, hasAlternativeName, DEAD-box helicase 20]
  • A. TARDBP
    TARDBP is a gene encoding the TDP-43 protein, a DNA/RNA-binding protein whose abnormal aggregation is a key pathological feature in amyotrophic lateral sclerosis and related neurodegenerative diseases.
  • B. U1 snRNP
    U1 snRNP is a small nuclear ribonucleoprotein complex essential for recognizing the 5′ splice site and initiating pre-mRNA splicing in eukaryotic cells.
  • C. FOXA2 transcription factor
    FOXA2 transcription factor is a forkhead box transcription factor that plays a key role in regulating genes involved in pancreatic beta-cell function, glucose metabolism, and endoderm development.
  • D. Cdh1
    Cdh1 is a regulatory protein that activates the anaphase-promoting complex/cyclosome (APC/C) to control mitotic exit and G1 phase progression in the cell cycle.
  • E. TATA-box binding protein associated factor 15
    TATA-box binding protein associated factor 15 (TAF15) is an RNA- and DNA-binding protein of the FET family involved in transcriptional regulation and RNA processing, and is implicated in certain cancers through gene fusions.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: DEAD-box helicase 20
Target entity description: DEAD-box helicase 20 is an ATP-dependent RNA helicase involved in RNA processing and ribonucleoprotein complex assembly, encoded by the human DDX20 gene.
  • A. TARDBP
    TARDBP is a gene encoding the TDP-43 protein, a DNA/RNA-binding protein whose abnormal aggregation is a key pathological feature in amyotrophic lateral sclerosis and related neurodegenerative diseases.
  • B. U2 snRNP
    U2 snRNP is a small nuclear ribonucleoprotein complex that recognizes the branch point sequence in pre-mRNA and plays a key role in spliceosome-mediated RNA splicing.
  • C. U1 snRNP
    U1 snRNP is a small nuclear ribonucleoprotein complex essential for recognizing the 5′ splice site and initiating pre-mRNA splicing in eukaryotic cells.
  • D. FOXA2 transcription factor
    FOXA2 transcription factor is a forkhead box transcription factor that plays a key role in regulating genes involved in pancreatic beta-cell function, glucose metabolism, and endoderm development.
  • E. Cdh1
    Cdh1 is a regulatory protein that activates the anaphase-promoting complex/cyclosome (APC/C) to control mitotic exit and G1 phase progression in the cell cycle.
  • F. None of above. chosen

Provenance (2 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_69e2458185f88190b0045227ee420411 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17cd9b3c0819096050f43a829ec0d completed April 29, 2026, 3:36 a.m.
Created at: April 17, 2026, 3:30 p.m.