Triple

T31440195
Position Surface form Disambiguated ID Type / Status
Subject hematopoietic stem cells E802042 entity
Predicate differentiationControlledBy P138498 FINISHED
Object transcription factor GATA-2
Transcription factor GATA-2 is a zinc finger DNA-binding protein crucial for the development, maintenance, and proliferation of hematopoietic stem and progenitor cells.
 E1963032 NE FINISHED

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: transcription factor GATA-2 | Statement: [hematopoietic stem cells, differentiationControlledBy, transcription factor GATA-2]
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: transcription factor GATA-2
Triple: [hematopoietic stem cells, differentiationControlledBy, transcription factor GATA-2]
Generated description
Transcription factor GATA-2 is a zinc finger DNA-binding protein crucial for the development, maintenance, and proliferation of hematopoietic stem and progenitor cells.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: differentiationControlledBy
Context triple: [hematopoietic stem cells, differentiationControlledBy, transcription factor GATA-2]
  • A. differentiationProperty
    Indicates a property or characteristic that serves to distinguish one entity from another within a given context.
  • B. rangeControlledBy
    Indicates that the extent or scope of something is regulated, limited, or determined by another entity.
  • C. differentiatedFrom
    Indicates that one entity is distinguished or set apart from another by identifying differences between them.
  • D. differentiatesInto
    Indicates that one entity develops or transforms into another, typically representing a change in type, state, or specialization.
  • E. controlsOrControlled chosen
    Indicates that one entity has control over another entity or is itself under the control of that other entity.
  • F. None of above.

Provenance (6 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_69f348c5a6bc819092a557e95438976f completed April 30, 2026, 12:19 p.m.
NER Named-entity recognition batch_69f6a5f71b2c8190aade8a83f465be0c completed May 3, 2026, 1:33 a.m.
NED1 Entity disambiguation (via context triple) batch_6a2b077efc708190aa419c6094f4a99a completed June 11, 2026, 7:07 p.m.
NEDg Description generation batch_6a2b0846c0c88190b7c1b6a06e958fa3 completed June 11, 2026, 7:11 p.m.
NED2 Entity disambiguation (via description) batch_6a2b09b430388190832809716830d009 completed June 11, 2026, 7:17 p.m.
PD Predicate disambiguation batch_69f69fe66df08190958558d63ee623d9 completed May 3, 2026, 1:07 a.m.
Created at: April 30, 2026, 9:05 p.m.