Triple

T22693517
Position Surface form Disambiguated ID Type / Status
Subject EWSR1 E561108 entity
Predicate formsFusionWith P149326 FINISHED
Object ERG
ERG is an ETS family transcription factor proto-oncogene frequently implicated in cancers such as Ewing sarcoma and prostate cancer through gene fusions and dysregulated expression.
 E1551057 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: ERG | Statement: [EWSR1, formsFusionWith, ERG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ERG
Context triple: [EWSR1, formsFusionWith, ERG]
  • A. ERG
    ERG is a faction of Conservative Party MPs in the United Kingdom known for its strong support of Brexit and advocacy for Eurosceptic policies.
  • B. ERGA
    ERGA is a European advisory body that brings together national regulators to help coordinate and harmonize audiovisual media regulation across the EU.
  • C. ERI
    ERI is the Earthquake Research Institute of the University of Tokyo, a leading Japanese center for seismology and earthquake-related research.
  • D. ERI
    ERI is the former stock ticker symbol for Eldorado Resorts, a U.S.-based casino and hospitality company that later became part of Caesars Entertainment.
  • E. ERI
    ERI is the IATA airport code for Erie International Airport, a commercial airport serving Erie, Pennsylvania.
  • 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: ERG
Triple: [EWSR1, formsFusionWith, ERG]
Generated description
ERG is an ETS family transcription factor proto-oncogene frequently implicated in cancers such as Ewing sarcoma and prostate cancer through gene fusions and dysregulated expression.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ERG
Target entity description: ERG is an ETS family transcription factor proto-oncogene frequently implicated in cancers such as Ewing sarcoma and prostate cancer through gene fusions and dysregulated expression.
  • A. ERG
    ERG is a faction of Conservative Party MPs in the United Kingdom known for its strong support of Brexit and advocacy for Eurosceptic policies.
  • B. ERGA
    ERGA is a European advisory body that brings together national regulators to help coordinate and harmonize audiovisual media regulation across the EU.
  • C. ERI
    ERI is the Earthquake Research Institute of the University of Tokyo, a leading Japanese center for seismology and earthquake-related research.
  • D. ERI
    ERI is the former stock ticker symbol for Eldorado Resorts, a U.S.-based casino and hospitality company that later became part of Caesars Entertainment.
  • E. ERI
    ERI is the IATA airport code for Erie International Airport, a commercial airport serving Erie, Pennsylvania.
  • 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_69e2454d71b48190a1f80af9f82b6fcf completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1789c6ae481908975b7d27e7624ac completed April 29, 2026, 3:18 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b7ece75648190a841256cf08a72f8 completed May 18, 2026, 9:04 p.m.
NEDg Description generation batch_6a0b834f488c8190bee40bd1caea0e40 completed May 18, 2026, 9:23 p.m.
NED2 Entity disambiguation (via description) batch_6a0b8717b65c819089d29c1802d1ed55 completed May 18, 2026, 9:39 p.m.
Created at: April 17, 2026, 3:13 p.m.