Triple

T15610012
Position Surface form Disambiguated ID Type / Status
Subject Mallaig harbour E375262 entity
Predicate serves P98 FINISHED
Object Eigg E24629 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: Eigg | Statement: [Mallaig harbour, serves, Eigg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Eigg
Context triple: [Mallaig harbour, serves, Eigg]
  • A. Eigg chosen
    Eigg is a small, community-owned island in the Inner Hebrides of Scotland, known for its striking volcanic landscapes and pioneering renewable energy system.
  • B. Tiree
    Tiree is a small, low-lying Hebridean island off Scotland’s west coast, known for its sandy beaches, sunshine, and strong windsurfing conditions.
  • C. Arran
    Arran is a historical region in the South Caucasus, largely corresponding to parts of modern-day Azerbaijan between the Kura and Aras rivers.
  • D. Arran
    Arran is a Scottish island in the Firth of Clyde known for its rugged mountains, scenic coastline, and rich archaeological and cultural heritage.
  • E. Colonsay
    Colonsay is a small Hebridean island off the west coast of Scotland, known for its rugged coastline, sandy beaches, and rich wildlife.
  • 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_69d85ccf2794819096cda4cbcb02d478 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e8024948190a6c711f2e5c2aac4 completed April 16, 2026, 2:50 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0035450810819092796c556dfa8ed3 completed May 10, 2026, 7:35 a.m.
Created at: April 10, 2026, 4:13 a.m.