Triple

T15895627
Position Surface form Disambiguated ID Type / Status
Subject Coronagraph Instrument E385445 entity
Predicate alternativeName P39 FINISHED
Object CGI
CGI is a high-contrast Coronagraph Instrument designed to directly image and study exoplanets and circumstellar disks by blocking out starlight.
 E1182896 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: CGI | Statement: [Coronagraph Instrument, alternativeName, CGI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: CGI
Context triple: [Coronagraph Instrument, alternativeName, CGI]
  • A. CGI
    CGI is a standard protocol that enables web servers to execute external programs and dynamically generate web content in response to user requests.
  • B. Cg
    Cg is a high-level shading language developed by NVIDIA for programming graphics processing units, similar in design and purpose to HLSL.
  • C. CGA
    CGA (Color Graphics Adapter) is IBM's early color display standard for the original IBM PC, capable of low-resolution graphics and basic color text output.
  • D. CGA
    CGA is the ICAO airline designator assigned to Congo Airways, the flag carrier of the Democratic Republic of the Congo.
  • E. .cg
    .cg is the country code top-level domain (ccTLD) assigned to the Republic of the Congo for use in its internet addresses.
  • 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: CGI
Triple: [Coronagraph Instrument, alternativeName, CGI]
Generated description
CGI is a high-contrast Coronagraph Instrument designed to directly image and study exoplanets and circumstellar disks by blocking out starlight.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: CGI
Target entity description: CGI is a high-contrast Coronagraph Instrument designed to directly image and study exoplanets and circumstellar disks by blocking out starlight.
  • A. CGI
    CGI is a standard protocol that enables web servers to execute external programs and dynamically generate web content in response to user requests.
  • B. Cg
    Cg is a high-level shading language developed by NVIDIA for programming graphics processing units, similar in design and purpose to HLSL.
  • C. CGA
    CGA (Color Graphics Adapter) is IBM's early color display standard for the original IBM PC, capable of low-resolution graphics and basic color text output.
  • D. CGA
    CGA is the ICAO airline designator assigned to Congo Airways, the flag carrier of the Democratic Republic of the Congo.
  • E. .cg
    .cg is the country code top-level domain (ccTLD) assigned to the Republic of the Congo for use in its internet addresses.
  • 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_69d86da5b800819083a31be937d738b0 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e15638f5bc81908de13f4b6a52b60c completed April 16, 2026, 9:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb04b55ec8190a5b3513b2afa4f83 completed May 9, 2026, 10:08 p.m.
NEDg Description generation batch_69ffb13fdb6c819091c3ee5c1f199031 completed May 9, 2026, 10:12 p.m.
NED2 Entity disambiguation (via description) batch_69ffb208aef881909b3a00e0015c27df completed May 9, 2026, 10:15 p.m.
Created at: April 10, 2026, 4:51 a.m.