Triple

T17375402
Position Surface form Disambiguated ID Type / Status
Subject Cibolo E422422 entity
Predicate adjacentTo P224 FINISHED
Object Marion, Texas
Marion, Texas is a small rural town in Guadalupe County within the San Antonio metropolitan area.
E1458852 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: Marion, Texas | Statement: [Cibolo, adjacentTo, Marion, Texas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marion, Texas
Context triple: [Cibolo, adjacentTo, Marion, Texas]
  • A. Marshall, Texas
    Marshall, Texas is a small city in East Texas known as a regional cultural and educational center and for its prominence in federal patent litigation.
  • B. Mart, Texas
    Mart, Texas is a small rural city in Central Texas known for its tight-knit community and agricultural surroundings.
  • C. Martindale, Texas
    Martindale, Texas is a small rural city in Central Texas known for its historic charm and location along the San Marcos River.
  • D. Hamlin, Texas
    Hamlin, Texas is a small rural city in West Texas known historically for its agriculture and railroad roots.
  • E. Lockney, Texas
    Lockney, Texas is a small rural town in the Texas Panhandle known for its agricultural economy and close-knit community.
  • 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: Marion, Texas
Triple: [Cibolo, adjacentTo, Marion, Texas]
Generated description
Marion, Texas is a small rural town in Guadalupe County within the San Antonio metropolitan area.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Marion, Texas
Target entity description: Marion, Texas is a small rural town in Guadalupe County within the San Antonio metropolitan area.
  • A. Marshall, Texas
    Marshall, Texas is a small city in East Texas known as a regional cultural and educational center and for its prominence in federal patent litigation.
  • B. Mart, Texas
    Mart, Texas is a small rural city in Central Texas known for its tight-knit community and agricultural surroundings.
  • C. Martindale, Texas
    Martindale, Texas is a small rural city in Central Texas known for its historic charm and location along the San Marcos River.
  • D. Hamlin, Texas
    Hamlin, Texas is a small rural city in West Texas known historically for its agriculture and railroad roots.
  • E. Lockney, Texas
    Lockney, Texas is a small rural town in the Texas Panhandle known for its agricultural economy and close-knit community.
  • 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_69d889d6535c81908be333c01deaec4e completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43a6c864481908507290282cc6d25 completed April 19, 2026, 2:14 a.m.
NED1 Entity disambiguation (via context triple) batch_6a09276e98588190ad3bdb9d04a19584 completed May 17, 2026, 2:26 a.m.
NEDg Description generation batch_6a0928a53e3c8190a8e636f5f1387f73 completed May 17, 2026, 2:32 a.m.
NED2 Entity disambiguation (via description) batch_6a0929485ebc8190ab8bc316b3e802ca completed May 17, 2026, 2:34 a.m.
Created at: April 10, 2026, 5:44 a.m.