Triple

T17162050
Position Surface form Disambiguated ID Type / Status
Subject Saint Martin E416504 entity
Predicate hasMajorTown P316 FINISHED
Object Philipsburg E256435 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: Philipsburg | Statement: [Saint Martin, hasMajorTown, Philipsburg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Philipsburg
Context triple: [Saint Martin, hasMajorTown, Philipsburg]
  • A. Philipsburg chosen
    Philipsburg is the main commercial and tourist hub of the Dutch Caribbean island of Sint Maarten, known for its cruise port, shopping district, and historic waterfront.
  • B. Phillippsburg
    Phillippsburg is a historic town in southwestern Germany, known for its strategic fortress on the Rhine and its role in various European military conflicts.
  • C. Fraserburg
    Fraserburg is a small, historic town in South Africa’s semi-arid Karoo region, known for its sheep farming and wide, open landscapes.
  • D. Vieux Fort
    Vieux Fort is a major town in the south of Saint Lucia, known for its international airport, coastal location, and role as a commercial and transportation hub.
  • E. Georgiaville
    Georgiaville is a historic village and mill community located within the town of Smithfield in Providence County, Rhode Island.
  • 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_69d886d279c081909f8ff1f743ddeb69 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3f91258648190a40396067ba5ecd3 completed April 18, 2026, 9:35 p.m.
NED1 Entity disambiguation (via context triple) batch_6a01483969a48190a90268c9560b8cd7 completed May 11, 2026, 3:08 a.m.
Created at: April 10, 2026, 5:37 a.m.