Triple

T38438197
Position Surface form Disambiguated ID Type / Status
Subject Lefschetz number E904006 entity
Predicate sumsOver P43790 FINISHED
Object all homological degrees k 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: all homological degrees k | Statement: [Lefschetz number, sumsOver, all homological degrees k]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: sumsOver
Context triple: [Lefschetz number, sumsOver, all homological degrees k]
  • A. isSumOf
    Indicates that one quantity is the result of adding together two or more other quantities.
  • B. summatoryIdentity chosen
    Indicates that two expressions are identically equal when summed over a specified range, typically expressing an equality between a summation and an equivalent closed-form or alternative summation.
  • C. requiresUniqueRepresentationAsSum
    Indicates that something must have a single, uniquely determined way of being expressed as a sum of specified components or parts.
  • D. hasInfiniteSumSide
    Indicates that one side of a relationship or equation involves an infinite sum or series rather than a finite quantity.
  • E. hasMinimalSumOfReciprocals
    Indicates that the related entities are arranged or selected such that the sum of the reciprocals of certain associated values is as small as possible compared to alternatives.
  • 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_69f76e6a2024819081aa04f4932f89d2 completed May 3, 2026, 3:48 p.m.
NER Named-entity recognition batch_69fcce7afcd08190906cc3801152656a completed May 7, 2026, 5:40 p.m.
PD Predicate disambiguation batch_69fcccf140ec8190862d53388a5f40d7 completed May 7, 2026, 5:33 p.m.
Created at: May 3, 2026, 4:31 p.m.