Triple

T10966546
Position Surface form Disambiguated ID Type / Status
Subject Harding E259114 entity
Predicate hasVariant P455 FINISHED
Object Hardinge E668347 NE 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: Hardinge | Statement: [Harding, hasVariant, Hardinge]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hardinge
Context triple: [Harding, hasVariant, Hardinge]
  • A. Hardinge chosen
    Hardinge is a British noble family name historically associated with prominent military and colonial administrators in the United Kingdom.
  • B. Solidere
    Solidere is a Lebanese real estate company responsible for the post-civil war reconstruction and development of Beirut’s central district.
  • C. Kaiserstein
    Kaiserstein is a notable summit point on Austria’s Schneeberg massif, popular with hikers for its alpine views.
  • D. Ferrar Dolerite
    Ferrar Dolerite is a widespread Jurassic-age igneous rock formation in Antarctica, notable for forming prominent sills and cliffs within the Transantarctic Mountains.
  • E. Sandvik
    Sandvik is a coastal village on the island of Öland in southeastern Sweden, known for its historic windmill and scenic Baltic Sea shoreline.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d6aa88500c819097d7032ca578e74f completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d77149c0448190a66322fa696fdbda completed April 9, 2026, 9:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69e2d78156c48190a956dc22b9832bcb completed April 18, 2026, 12:59 a.m.
Created at: April 8, 2026, 9:24 p.m.