Triple

T8385444
Position Surface form Disambiguated ID Type / Status
Subject Max Da Costa E197806 entity
Predicate ally P4662 FINISHED
Object Spider E197808 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: Spider | Statement: [Max Da Costa, ally, Spider]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Spider
Context triple: [Max Da Costa, ally, Spider]
  • A. Spider
    Spider is a distributed storage engine for MariaDB that enables sharding and horizontal partitioning of tables across multiple servers.
  • B. Spider chosen
    Spider is the protagonist of the science fiction film "Elysium," a character who navigates a starkly divided future society to challenge its oppressive class system.
  • C. Spider
    "Spider" is a 2002 psychological drama film directed by David Cronenberg, in which Gabriel Byrne plays a key role in the story of a mentally disturbed man unraveling his traumatic past.
  • D. Spider
    Spider is a central trickster god character in Neil Gaiman's novel "Anansi Boys," embodying charm, mischief, and the supernatural legacy of the West African spider-god Anansi.
  • E. Black Spider
    Black Spider is the famous nickname of Soviet goalkeeper Lev Yashin, widely regarded as one of the greatest goalkeepers in football history.
  • 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_69ca82f749388190bffbea6dfb509016 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb80e03eb08190a458c9caa0524e0f completed March 31, 2026, 8:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69cde8312be48190bd5896adc8bb4e95 completed April 2, 2026, 3:53 a.m.
Created at: March 30, 2026, 6:02 p.m.