Triple

T14923651
Position Surface form Disambiguated ID Type / Status
Subject GaBoDS survey E371576 entity
Predicate acronym P43 FINISHED
Object GaBoDS
GaBoDS is an astronomical deep-field imaging survey that uses wide-field optical observations to study distant galaxies and large-scale structure in the universe.
 E1126292 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: GaBoDS | Statement: [GaBoDS survey, acronym, GaBoDS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: GaBoDS
Context triple: [GaBoDS survey, acronym, GaBoDS]
  • A. GBO
    GBO is the common abbreviation used for the Greensboro Grasshoppers minor league baseball team.
  • B. gemsbok
    The gemsbok is a large, striking antelope native to arid regions of southern Africa, recognized by its long, straight horns and bold black-and-white facial markings.
  • C. GOBD
    GOBD is the ICAO airport code for Blaise Diagne International Airport, the main international gateway serving Dakar, Senegal.
  • D. SDBOR
    SDBOR is the governing body responsible for overseeing South Dakota’s public universities and special schools.
  • E. OSDBU
    OSDBU is a U.S. federal government office that advocates for and oversees programs to ensure small and disadvantaged businesses have fair access to federal contracting opportunities.
  • 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: GaBoDS
Triple: [GaBoDS survey, acronym, GaBoDS]
Generated description
GaBoDS is an astronomical deep-field imaging survey that uses wide-field optical observations to study distant galaxies and large-scale structure in the universe.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: GaBoDS
Target entity description: GaBoDS is an astronomical deep-field imaging survey that uses wide-field optical observations to study distant galaxies and large-scale structure in the universe.
  • A. GBO
    GBO is the common abbreviation used for the Greensboro Grasshoppers minor league baseball team.
  • B. gemsbok
    The gemsbok is a large, striking antelope native to arid regions of southern Africa, recognized by its long, straight horns and bold black-and-white facial markings.
  • C. GOBD
    GOBD is the ICAO airport code for Blaise Diagne International Airport, the main international gateway serving Dakar, Senegal.
  • D. SDBOR
    SDBOR is the governing body responsible for overseeing South Dakota’s public universities and special schools.
  • E. OSDBU
    OSDBU is a U.S. federal government office that advocates for and oversees programs to ensure small and disadvantaged businesses have fair access to federal contracting opportunities.
  • 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_69d85cc7ea3481908228b5acb7d06f12 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded6323f8c8190af02d06352d459c3 completed April 15, 2026, 12:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe72c3185c8190af2cd0329d701caa completed May 8, 2026, 11:33 p.m.
NEDg Description generation batch_69fe73dd1058819081e6c44a9684faa8 completed May 8, 2026, 11:38 p.m.
NED2 Entity disambiguation (via description) batch_69fe749bded08190ac872fddbd5d3004 completed May 8, 2026, 11:41 p.m.
Created at: April 10, 2026, 2:34 a.m.