Triple

T25751008
Position Surface form Disambiguated ID Type / Status
Subject Sentinel-6 Michael Freilich E648467 entity
Predicate hasTwinSatellite P159230 FINISHED
Object Sentinel-6B NE NERFINISHED

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: Sentinel-6B | Statement: [Sentinel-6 Michael Freilich, hasTwinSatellite, Sentinel-6B]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasTwinSatellite
Context triple: [Sentinel-6 Michael Freilich, hasTwinSatellite, Sentinel-6B]
  • A. hasTwin
    Indicates that one entity is a twin of another, sharing the same birth event or time with a sibling.
  • B. hasTwinStatus
    Indicates that an entity has a twin relationship or classification, such as being one of a pair of twins or having an associated twin counterpart.
  • C. hasTwinFeature
    Indicates that two entities share an identical or nearly identical feature, characteristic, or component, as if they are twins in that respect.
  • D. isTwinWith
    Indicates that two entities are twins, sharing the same birth parents and being born at (or very near) the same time.
  • E. hasTwinSystemWith
    Indicates that two systems are twins, meaning they are closely paired or mirrored counterparts in structure, function, or configuration.
  • 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_69e7ab314d788190b3abe19e114080e1 completed April 21, 2026, 4:52 p.m.
NER Named-entity recognition batch_69f5fd7ef3c48190b5f1b3b4e9cecb2b completed May 2, 2026, 1:34 p.m.
PD Predicate disambiguation batch_69f4938262ac8190b41f922d0407d272 completed May 1, 2026, 11:50 a.m.
PDg Predicate description generation batch_69f497b8abb88190bb672cf6907c4b8d completed May 1, 2026, 12:08 p.m.
Created at: April 22, 2026, 4:35 a.m.