Triple

T12902683
Position Surface form Disambiguated ID Type / Status
Subject Eiger north face E308648 entity
Predicate hasNickname P39 FINISHED
Object Mordwand E506290 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: Mordwand | Statement: [Eiger north face, hasNickname, Mordwand]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mordwand
Context triple: [Eiger north face, hasNickname, Mordwand]
  • A. Mordwand chosen
    Mordwand is the ominous German nickname, meaning "murder wall," for the notoriously dangerous north face of the Eiger in the Bernese Alps.
  • B. The Mangler
    The Mangler is a horror short story by Stephen King about a possessed industrial laundry machine that becomes the source of gruesome deaths.
  • C. Morella
    Morella is a historic walled hilltop town in eastern Spain renowned for its medieval castle and well-preserved old quarter.
  • D. Zabivaka
    Zabivaka is the wolf character that served as the official mascot for major international football tournaments hosted by Russia, including the 2018 FIFA World Cup.
  • E. The Cellar
    The Cellar is the original title of the 2016 psychological thriller film that was later released as 10 Cloverfield Lane.
  • 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_69d7bdf7c1f0819098102569a8d8cbf5 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d971820e008190bf8bc7c392c8bcbb completed April 10, 2026, 9:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6a563a84c8190a75d830653661518 completed May 3, 2026, 1:31 a.m.
Created at: April 9, 2026, 5:40 p.m.