Triple

T2364584
Position Surface form Disambiguated ID Type / Status
Subject Riemann–Roch theorem E47350 entity
Predicate hasModernFormulationIn P38255 FINISHED
Object sheaf cohomology 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: sheaf cohomology | Statement: [Riemann–Roch theorem, hasModernFormulationIn, sheaf cohomology]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasModernFormulationIn
Context triple: [Riemann–Roch theorem, hasModernFormulationIn, sheaf cohomology]
  • A. hasFormulation
    Indicates that one entity is expressed, prepared, or configured in a particular form or composition defined by another entity.
  • B. hasFormulationType
    Indicates the specific way something is physically prepared or presented, such as its dosage form, composition, or delivery format.
  • C. modernFormSince
    Indicates that an entity has existed in its current or modern form starting from a specified point in time.
  • D. hasModernEditions
    Indicates that an original work or text has one or more updated or contemporary published editions.
  • E. hasTraditionalFormIn
    Indicates that something possesses a customary or historically established form or representation within a specified context, system, or location.
  • 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_69a88a1a4a6081908645b0f2914521ab completed March 4, 2026, 7:38 p.m.
NER Named-entity recognition batch_69abc7486cb48190acef1891cc87bdb1 completed March 7, 2026, 6:35 a.m.
PD Predicate disambiguation batch_69abc599b92c819093d9e15d4437705d completed March 7, 2026, 6:28 a.m.
PDg Predicate description generation batch_69abc6a85e2c8190afec217ff29476be completed March 7, 2026, 6:33 a.m.
Created at: March 4, 2026, 7:55 p.m.