Triple

T20859733
Position Surface form Disambiguated ID Type / Status
Subject Sarah Williams E513582 entity
Predicate alliesWith P435 FINISHED
Object Ludo 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: Ludo | Statement: [Sarah Williams, alliesWith, Ludo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ludo
Context triple: [Sarah Williams, alliesWith, Ludo]
  • A. Ludo chosen
    Ludo is a gentle, horned beast-like creature from the fantasy film "Labyrinth" who befriends Sarah and helps her navigate the Goblin King's maze.
  • B. Ludo
    Ludo is a common short form or nickname for the given name Ludovica.
  • C. Snakes and Ladders
    Snakes and Ladders is a 1960s novel by British actor and writer Dirk Bogarde, blending autobiographical elements with reflective, character-driven storytelling.
  • D. Parchís
    Parchís was a popular Spanish children's music group from the late 1970s and 1980s known for their catchy songs and colorful, board-game-inspired image.
  • E. LudoWic
    LudoWic is a music artist known for creating atmospheric, electronic-driven soundtracks and compositions.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4f5b01081909452f654d2fc3f50 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c3aabef4819098f0fd24dcc27dbd completed April 21, 2026, 12:24 a.m.
Created at: April 16, 2026, 12:44 p.m.