Triple

T19281121
Position Surface form Disambiguated ID Type / Status
Subject Messier 19 E482188 entity
Predicate ellipticity P135430 FINISHED
Object high compared to typical globular clusters 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: high compared to typical globular clusters | Statement: [Messier 19, ellipticity, high compared to typical globular clusters]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: ellipticity
Context triple: [Messier 19, ellipticity, high compared to typical globular clusters]
  • A. ellipsoid
    Indicates that one entity has the geometric shape or form of an ellipsoid in relation to another or within a given context.
  • B. isEccentric
    Indicates that an entity behaves or appears in a way that deviates noticeably from conventional or expected norms.
  • C. hasEccentricity
    Indicates that an object or orbit possesses a specific degree of deviation from being perfectly circular, quantified by its eccentricity value.
  • D. orbitalEccentricity
    Indicates the degree to which an orbit deviates from a perfect circle, quantifying how elongated the orbital path is.
  • E. eccentricityClass
    Indicates the classification of how unconventional or atypical an entity’s behavior, properties, or characteristics are relative to a defined norm.
  • F. None of above. chosen

Provenance (4 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_69d8e8cf61b0819096fe3e4107827c4e completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5fbff1e6c819094ae6a5ad40adb65 completed April 20, 2026, 10:12 a.m.
PD Predicate disambiguation batch_69e4dd07a7208190afcd51ba1dc87c33 completed April 19, 2026, 1:47 p.m.
PDg Predicate description generation batch_69e4df51ac6c819091ce72b07790ffa6 completed April 19, 2026, 1:57 p.m.
Created at: April 10, 2026, 1:30 p.m.