Triple

T704292
Position Surface form Disambiguated ID Type / Status
Subject Equifax E14065 entity
Predicate hasSubsidiary P254 FINISHED
Object Talx
Talx is a workforce solutions and employment verification company that operates as a subsidiary of the credit reporting agency Equifax.
 E85148 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: Talx | Statement: [Equifax, hasSubsidiary, Talx]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Talx
Context triple: [Equifax, hasSubsidiary, Talx]
  • A. Calca
    Calca is a small Andean town in Peru’s Sacred Valley, known for its traditional Quechua culture and proximity to Inca archaeological sites.
  • B. Shilha
    Shilha is a major Berber (Amazigh) language of southwestern Morocco, spoken primarily by the Shilha people in the Atlas and Anti-Atlas regions.
  • C. Boric
    Boric is the surname of Gabriel Boric, the Chilean politician who became one of the world’s youngest heads of state when he was elected President of Chile.
  • D. Tahlequah
    Tahlequah is a city in eastern Oklahoma that serves as the capital of the Cherokee Nation and is known for its rich Native American history and culture.
  • E. Lycon
    Lycon was one of the lesser-known Athenian accusers of Socrates, traditionally identified as representing the interests of the orators in the trial that led to Socrates’ execution.
  • 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: Talx
Triple: [Equifax, hasSubsidiary, Talx]
Generated description
Talx is a workforce solutions and employment verification company that operates as a subsidiary of the credit reporting agency Equifax.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Talx
Target entity description: Talx is a workforce solutions and employment verification company that operates as a subsidiary of the credit reporting agency Equifax.
  • A. Calca
    Calca is a small Andean town in Peru’s Sacred Valley, known for its traditional Quechua culture and proximity to Inca archaeological sites.
  • B. Shilha
    Shilha is a major Berber (Amazigh) language of southwestern Morocco, spoken primarily by the Shilha people in the Atlas and Anti-Atlas regions.
  • C. Boric
    Boric is the surname of Gabriel Boric, the Chilean politician who became one of the world’s youngest heads of state when he was elected President of Chile.
  • D. Tahlequah
    Tahlequah is a city in eastern Oklahoma that serves as the capital of the Cherokee Nation and is known for its rich Native American history and culture.
  • E. Lycon
    Lycon was one of the lesser-known Athenian accusers of Socrates, traditionally identified as representing the interests of the orators in the trial that led to Socrates’ execution.
  • 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_69a493494ec48190ae6751683625a9ba completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a533fa788190bba0f55655469c46 completed March 1, 2026, 8:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69a5dcae2ef88190a9ea1604429f048a completed March 2, 2026, 6:53 p.m.
NEDg Description generation batch_69a5df14e1788190bb2f2cc87cadcb40 completed March 2, 2026, 7:03 p.m.
NED2 Entity disambiguation (via description) batch_69a5ff5dd4808190bb8ae25fbdca0075 completed March 2, 2026, 9:21 p.m.
Created at: March 1, 2026, 7:36 p.m.