Triple

T5446449
Position Surface form Disambiguated ID Type / Status
Subject Edom E122259 entity
Predicate hasRegion P285 FINISHED
Object Mount Seir E368559 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: Mount Seir | Statement: [Edom, hasRegion, Mount Seir]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mount Seir
Context triple: [Edom, hasRegion, Mount Seir]
  • A. Mount Seir chosen
    Mount Seir is a mountainous region in the ancient Near East, traditionally identified as the homeland of Esau and the nation of Edom in the Hebrew Bible.
  • B. Mount Voras
    Mount Voras is a prominent mountain on the border between Greece and North Macedonia, known for its ski resort and scenic alpine landscapes.
  • C. Mount Taron
    Mount Taron is the tallest mountain on New Ireland Island in Papua New Guinea, known for its rugged terrain and dense tropical rainforest.
  • D. Mount Oros
    Mount Oros is the highest mountain on the Greek island of Aegina, known for its panoramic views and historical religious sites.
  • E. Mount Ziria
    Mount Ziria is a prominent mountain in the Peloponnese region of Greece, known for its rugged landscapes, hiking trails, and mythological association with the god Hermes.
  • 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_69bd4640f52c81909e653ec361f66d76 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd91cf5d488190868ffefad02c7a04 completed March 20, 2026, 6:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69bfd23af5988190a66bdbec54654970 completed March 22, 2026, 11:27 a.m.
Created at: March 20, 2026, 2:07 p.m.