Triple

T20326996
Position Surface form Disambiguated ID Type / Status
Subject Tucana V E492363 entity
Predicate morphologicalDescription P48546 FINISHED
Object ultra-diffuse LITERAL FINISHED

How this triple was built (2 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: ultra-diffuse | Statement: [Tucana V, morphologicalDescription, ultra-diffuse]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: morphologicalDescription
Context triple: [Tucana V, morphologicalDescription, ultra-diffuse]
  • A. morphologicalComparison
    Indicates a relationship where two or more entities are compared based on differences or similarities in their morphological (form or structural) characteristics.
  • B. morphologicalDiversity
    Indicates variation in the forms, structures, or shapes of entities within a group or system.
  • C. morphologicalRole
    Indicates the specific functional role that a morphological element (such as an affix or morpheme) plays within the structure or formation of a word.
  • D. relatedMorphologicalFeature
    Indicates that one entity is connected to another through a shared or corresponding morphological feature or structure.
  • E. notableMorphology chosen
    Indicates that an entity is characterized by a distinctive or noteworthy physical form, structure, or shape.
  • F. None of above.

Provenance (3 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_69e0b4a0134081909113563e1c3ba68a completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e677e4130081909ec54f131939e442 completed April 20, 2026, 7 p.m.
PD Predicate disambiguation batch_69e5762655ac8190a8cc48a29fa2c0c4 completed April 20, 2026, 12:41 a.m.
Created at: April 16, 2026, 11:21 a.m.