Triple

T8357363
Position Surface form Disambiguated ID Type / Status
Subject Excavata E196712 entity
Predicate includesTaxon P1393 FINISHED
Object Discoba group
The Discoba group is a major clade of unicellular eukaryotes within the Excavata supergroup, encompassing diverse flagellated protists such as euglenids and kinetoplastids.
E728820 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: Discoba group | Statement: [Excavata, includesTaxon, Discoba group]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Discoba group
Context triple: [Excavata, includesTaxon, Discoba group]
  • A. Palisaide group
    The Palisaide group is a mountain group or range that includes Starlight Peak among its summits.
  • B. Badaic group
    The Badaic group is a subgroup of related Austronesian languages spoken in parts of Central Sulawesi, Indonesia.
  • C. Parâng group
    The Parâng group is a prominent mountain massif in Romania known for its high peaks, glacial lakes, and popular hiking and skiing areas.
  • D. Pertnjara Group
    The Pertnjara Group is a geological rock unit within central Australia's Amadeus Basin, known for its sedimentary sequences that record Paleozoic depositional environments.
  • E. Incursori Group
    The Incursori Group is an elite Italian Navy special operations unit specializing in maritime commando, sabotage, and reconnaissance missions.
  • 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: Discoba group
Triple: [Excavata, includesTaxon, Discoba group]
Generated description
The Discoba group is a major clade of unicellular eukaryotes within the Excavata supergroup, encompassing diverse flagellated protists such as euglenids and kinetoplastids.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Discoba group
Target entity description: The Discoba group is a major clade of unicellular eukaryotes within the Excavata supergroup, encompassing diverse flagellated protists such as euglenids and kinetoplastids.
  • A. Palisaide group
    The Palisaide group is a mountain group or range that includes Starlight Peak among its summits.
  • B. Badaic group
    The Badaic group is a subgroup of related Austronesian languages spoken in parts of Central Sulawesi, Indonesia.
  • C. Parâng group
    The Parâng group is a prominent mountain massif in Romania known for its high peaks, glacial lakes, and popular hiking and skiing areas.
  • D. Pertnjara Group
    The Pertnjara Group is a geological rock unit within central Australia's Amadeus Basin, known for its sedimentary sequences that record Paleozoic depositional environments.
  • E. Incursori Group
    The Incursori Group is an elite Italian Navy special operations unit specializing in maritime commando, sabotage, and reconnaissance missions.
  • 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_69ca82f08b348190bfb7881944bbff6f completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb804b57f88190907a4e4e389caf5f completed March 31, 2026, 8:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69cdc76d49c881909e8e93b8f7d940df completed April 2, 2026, 1:33 a.m.
NEDg Description generation batch_69cdcc872cc081909c75b3fb08b03e3f completed April 2, 2026, 1:55 a.m.
NED2 Entity disambiguation (via description) batch_69cdd15b53748190966a94b7e8c04880 completed April 2, 2026, 2:15 a.m.
Created at: March 30, 2026, 5:59 p.m.