Triple

T11516072
Position Surface form Disambiguated ID Type / Status
Subject Wapama E273033 entity
Predicate shipName P14494 FINISHED
Object Wapama E273033 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: Wapama | Statement: [Wapama, shipName, Wapama]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wapama
Context triple: [Wapama, shipName, Wapama]
  • A. Wapama chosen
    Wapama was a historic wooden steam schooner built in 1915 that served the West Coast lumber trade and later became a preserved museum ship in San Francisco before being dismantled.
  • B. Waipawa
    Waipawa is a small rural service town in New Zealand’s Hawke’s Bay region, known for its agricultural surroundings and historic character.
  • C. Waibakul
    Waibakul is a town on the island of Sumba in Indonesia that serves as the administrative and political center of Central Sumba Regency.
  • D. Nakaseke
    Nakaseke is a district in central Uganda that lies within the traditional kingdom of Buganda.
  • E. Piranga
    Piranga is a genus of brightly colored New World songbirds in the cardinal family, commonly known as tanagers.
  • 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_69d6aae2c3748190bed2ea50dfb160dc completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d87fcc72a48190b81acedfcc8685d3 completed April 10, 2026, 4:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69e625143a608190a1119b30c08df0fd completed April 20, 2026, 1:07 p.m.
Created at: April 8, 2026, 9:36 p.m.