Triple

T7240138
Position Surface form Disambiguated ID Type / Status
Subject Colbert County E155332 entity
Predicate namedAfter P63 FINISHED
Object Levi Colbert
Levi Colbert was a prominent early 19th-century Chickasaw leader and negotiator known for his role in treaty discussions with the United States government.
 E654421 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: Levi Colbert | Statement: [Colbert County, namedAfter, Levi Colbert]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Levi Colbert
Context triple: [Colbert County, namedAfter, Levi Colbert]
  • A. Caleb Speir
    Caleb Speir is a writer known for his work on the television series "American Boy."
  • B. Luke Collins
    Luke Collins is a fictional professional bull rider and romantic lead in Nicholas Sparks' novel and film adaptation "The Longest Ride."
  • C. Levi Sanders
    Levi Sanders is an American political consultant and public defender best known as the son of U.S. Senator and progressive figure Bernie Sanders.
  • D. Brody Smith
    Brody Smith is an actor known for playing the character Pugsley Addams in an adaptation of "The Addams Family."
  • E. Brody Brown
    Brody Brown is an American songwriter, producer, and multi-instrumentalist best known for his extensive work with Bruno Mars and contributions to numerous contemporary R&B and pop hits.
  • 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: Levi Colbert
Triple: [Colbert County, namedAfter, Levi Colbert]
Generated description
Levi Colbert was a prominent early 19th-century Chickasaw leader and negotiator known for his role in treaty discussions with the United States government.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Levi Colbert
Target entity description: Levi Colbert was a prominent early 19th-century Chickasaw leader and negotiator known for his role in treaty discussions with the United States government.
  • A. Caleb Speir
    Caleb Speir is a writer known for his work on the television series "American Boy."
  • B. Luke Collins
    Luke Collins is a fictional professional bull rider and romantic lead in Nicholas Sparks' novel and film adaptation "The Longest Ride."
  • C. Levi Sanders
    Levi Sanders is an American political consultant and public defender best known as the son of U.S. Senator and progressive figure Bernie Sanders.
  • D. Brody Smith
    Brody Smith is an actor known for playing the character Pugsley Addams in an adaptation of "The Addams Family."
  • E. Brody Brown
    Brody Brown is an American songwriter, producer, and multi-instrumentalist best known for his extensive work with Bruno Mars and contributions to numerous contemporary R&B and pop hits.
  • 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_69c688143bfc81908d4176617735e601 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6ea39230481908401ead83d8666cd completed March 27, 2026, 8:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7db0fd90881908c6b84f1292f0b01 completed March 28, 2026, 1:43 p.m.
NEDg Description generation batch_69c7df2bb57c81909f08b565fe739166 completed March 28, 2026, 2:01 p.m.
NED2 Entity disambiguation (via description) batch_69c7df7c65e481908eb5c92168429d5a completed March 28, 2026, 2:02 p.m.
Created at: March 27, 2026, 2:55 p.m.