Triple

T12532759
Position Surface form Disambiguated ID Type / Status
Subject Piran E299609 entity
Predicate hasPort P35 FINISHED
Object Piran harbor E451300 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: Piran harbor | Statement: [Piran, hasPort, Piran harbor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Piran harbor
Context triple: [Piran, hasPort, Piran harbor]
  • A. Piran Bay chosen
    Piran Bay is a small bay in the northern Adriatic Sea, known for its picturesque coastline and the historic Slovenian town of Piran on its shore.
  • B. Pothia harbor
    Pothia harbor is the main port and waterfront area of Kalymnos, serving as the island’s central hub for transport, fishing, and local commerce.
  • C. Avarua Harbour
    Avarua Harbour is the main coastal port and anchorage serving the town of Avarua on Rarotonga in the Cook Islands.
  • D. Ajos harbour
    Ajos harbour is a key Finnish seaport area near Kemi that serves as an important hub for cargo handling and maritime transport in the northern Baltic Sea.
  • E. Sauda harbour
    Sauda harbour is a port facility in the town of Sauda in western Norway, serving local industry and maritime transport in the surrounding fjord region.
  • 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_69d6ada5cdd48190860d9ce30aff69be completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d9546b8fd48190ae90e80785b2e2d1 completed April 10, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69f64bc8866c81908821525b595715e2 completed May 2, 2026, 7:08 p.m.
Created at: April 8, 2026, 9:57 p.m.