Triple

T16194089
Position Surface form Disambiguated ID Type / Status
Subject Siege of Perpignan E393015 entity
Predicate fortressCity P11105 FINISHED
Object Perpignan E164948 NE FINISHED

How this triple was built (3 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: Perpignan | Statement: [Siege of Perpignan, fortressCity, Perpignan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Perpignan
Context triple: [Siege of Perpignan, fortressCity, Perpignan]
  • A. Perpignan chosen
    Perpignan is a historic city in southern France near the Spanish border, known for its Catalan culture and Mediterranean climate.
  • B. Béziers
    Béziers is a historic city in southern France known for its wine production, ancient Roman heritage, and the famous Feria de Béziers festival.
  • C. Montpellier
    Montpellier is a major city in southern France known for its medieval old town, vibrant university life, and proximity to the Mediterranean coast.
  • D. Montpellier
    Montpellier is an affluent district of Cheltenham, England, known for its Regency architecture, boutique shops, and café culture.
  • E. Marseillan
    Marseillan is a coastal commune in southern France known for its historic port, oyster farming, and proximity to the Étang de Thau lagoon.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: fortressCity
Context triple: [Siege of Perpignan, fortressCity, Perpignan]
  • A. isFortifiedCity chosen
    Indicates that a city is strengthened with defensive structures or fortifications, such as walls, ramparts, or similar protective works.
  • B. fortifiedBuilding
    Indicates that a building is strengthened or reinforced for defense against attacks or intrusions.
  • C. fortifiedSite
    Indicates a site that has been strengthened or defended with protective structures or measures against attack.
  • D. fortressOriginallyBuiltBy
    Indicates that a particular fortress was initially constructed by a specified builder or group.
  • E. fortificationTypeBesieged
    Indicates that a specific type of fortification is the target of a siege or besieging action.
  • F. None of above.

Provenance (4 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_69d87f1e49ac8190a311b54d32990576 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e222d851188190b2452d165e4fc4bd completed April 17, 2026, 12:08 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00606a3d5c8190a145ca35ce458f7e completed May 10, 2026, 10:39 a.m.
PD Predicate disambiguation batch_69e219e11f6081909106b1240a17fd37 completed April 17, 2026, 11:30 a.m.
Created at: April 10, 2026, 5:02 a.m.