Triple

T13462748
Position Surface form Disambiguated ID Type / Status
Subject Real County, Texas E311412 entity
Predicate countySeat P383 FINISHED
Object Leakey, Texas
Leakey, Texas is a small town in the Texas Hill Country known as a gateway to outdoor recreation along the Frio River.
E1218559 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: Leakey, Texas | Statement: [Real County, Texas, countySeat, Leakey, Texas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leakey, Texas
Context triple: [Real County, Texas, countySeat, Leakey, Texas]
  • A. Leo, Texas
    Leo, Texas is a small rural unincorporated community located in Cooke County in north-central Texas.
  • B. Leonard, Texas
    Leonard, Texas is a small rural city in North Texas known for its tight-knit community and annual Leonard Picnic celebration.
  • C. Lockhart, Texas
    Lockhart, Texas is a small Central Texas city renowned as the "Barbecue Capital of Texas" and a historic hub of the Austin–San Antonio region.
  • D. Millican, Texas
    Millican, Texas is a small rural community in east-central Texas known for its historic role as an early railroad town.
  • E. Keene, Texas
    Keene, Texas is a small city in North Texas known for its close-knit community and association with Southwestern Adventist University.
  • 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: Leakey, Texas
Triple: [Real County, Texas, countySeat, Leakey, Texas]
Generated description
Leakey, Texas is a small town in the Texas Hill Country known as a gateway to outdoor recreation along the Frio River.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Leakey, Texas
Target entity description: Leakey, Texas is a small town in the Texas Hill Country known as a gateway to outdoor recreation along the Frio River.
  • A. Leo, Texas
    Leo, Texas is a small rural unincorporated community located in Cooke County in north-central Texas.
  • B. Leonard, Texas
    Leonard, Texas is a small rural city in North Texas known for its tight-knit community and annual Leonard Picnic celebration.
  • C. Lockhart, Texas
    Lockhart, Texas is a small Central Texas city renowned as the "Barbecue Capital of Texas" and a historic hub of the Austin–San Antonio region.
  • D. Millican, Texas
    Millican, Texas is a small rural community in east-central Texas known for its historic role as an early railroad town.
  • E. Keene, Texas
    Keene, Texas is a small city in North Texas known for its close-knit community and association with Southwestern Adventist University.
  • 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_69d806a938b8819097ec43a2229fc7f9 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dbaf0d95fc81909d9f73d5315dc7b4 completed April 12, 2026, 2:41 p.m.
NED1 Entity disambiguation (via context triple) batch_6a006065741c8190ad4ceb6bd3d60f9f completed May 10, 2026, 10:39 a.m.
NEDg Description generation batch_6a00620e66788190acccf2c8fce00943 completed May 10, 2026, 10:46 a.m.
NED2 Entity disambiguation (via description) batch_6a0062665d908190b8127b21edcad30e completed May 10, 2026, 10:48 a.m.
Created at: April 9, 2026, 9:41 p.m.