Triple

T10008072
Position Surface form Disambiguated ID Type / Status
Subject Boxer E198301 entity
Predicate track P17929 FINISHED
Object Ada
Ada is a competitive boxer known for her performances in the ring.
 E834661 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: Ada | Statement: [Boxer, track, Ada]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ada
Context triple: [Boxer, track, Ada]
  • A. Ada
    Ada is the given name of Ada Yonath, the Nobel Prize–winning Israeli crystallographer renowned for her pioneering work on the structure of the ribosome.
  • B. Ada
    Ada is a small city in south-central Oklahoma known as the county seat of Pontotoc County and home to East Central University and the headquarters of the Chickasaw Nation.
  • C. Ada
    Ada is a coastal town and traditional Ga-Adangbe community in the Greater Accra Region of Ghana, known for its estuary, beaches, and cultural heritage.
  • D. Ada
    Ada is a town in northern Serbia's Vojvodina region, known for its Hungarian ethnic majority and location along the Tisa River.
  • E. Ada (programming language)
    Ada is a statically typed, high-level programming language designed with strong support for reliability, safety, and real-time systems, widely used in mission-critical and embedded applications such as aerospace and defense.
  • 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: Ada
Triple: [Boxer, track, Ada]
Generated description
Ada is a competitive boxer known for her performances in the ring.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ada
Target entity description: Ada is a competitive boxer known for her performances in the ring.
  • A. Ada
    Ada is the given name of Ada Yonath, the Nobel Prize–winning Israeli crystallographer renowned for her pioneering work on the structure of the ribosome.
  • B. Ada
    Ada is a small city in south-central Oklahoma known as the county seat of Pontotoc County and home to East Central University and the headquarters of the Chickasaw Nation.
  • C. Ada
    Ada is a coastal town and traditional Ga-Adangbe community in the Greater Accra Region of Ghana, known for its estuary, beaches, and cultural heritage.
  • D. Ada
    Ada is a town in northern Serbia's Vojvodina region, known for its Hungarian ethnic majority and location along the Tisa River.
  • E. Ada (programming language)
    Ada is a statically typed, high-level programming language designed with strong support for reliability, safety, and real-time systems, widely used in mission-critical and embedded applications such as aerospace and defense.
  • 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_69ca830fcca48190bbbd9b20c233835f completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cdcd187fe481908556ea896c528ea4 completed April 2, 2026, 1:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69d26a683c208190a79ebc2e6ec5893c completed April 5, 2026, 1:58 p.m.
NEDg Description generation batch_69d26b4060548190980bd01ef550c4bd completed April 5, 2026, 2:01 p.m.
NED2 Entity disambiguation (via description) batch_69d26bf054608190890377e9b7538842 completed April 5, 2026, 2:04 p.m.
Created at: March 30, 2026, 8:52 p.m.