Triple

T2227653
Position Surface form Disambiguated ID Type / Status
Subject Shandaken Tunnel E48689 entity
Predicate connectsReservoir P36347 FINISHED
Object Schoharie Reservoir E62829 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: Schoharie Reservoir | Statement: [Shandaken Tunnel, connectsReservoir, Schoharie Reservoir]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Schoharie Reservoir
Context triple: [Shandaken Tunnel, connectsReservoir, Schoharie Reservoir]
  • A. Schoharie Reservoir chosen
    Schoharie Reservoir is a major upstate New York water supply reservoir that forms part of the New York City water system.
  • B. Neversink Reservoir
    Neversink Reservoir is a major Catskill Mountain water supply reservoir in New York that forms part of New York City’s upstate drinking water system.
  • C. Croton Falls Reservoir
    Croton Falls Reservoir is a man-made lake in Westchester County, New York, that serves as part of New York City's Croton water supply system.
  • D. Kensico Reservoir
    Kensico Reservoir is a major New York City water supply reservoir located in Westchester County, New York, known for its role in storing and regulating drinking water from the Catskill and Delaware systems.
  • E. Rondout Reservoir
    Rondout Reservoir is a major New York City water supply reservoir in the Catskill Mountains, formed by damming Rondout Creek and serving as a key component of the city’s Catskill–Delaware water system.
  • 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: connectsReservoir
Context triple: [Shandaken Tunnel, connectsReservoir, Schoharie Reservoir]
  • A. reservoir
    Indicates that one entity serves as a storage or containment source (often for a resource) that can supply or affect another entity.
  • B. connectsViaCanal
    Indicates that one entity is linked or joined to another by means of a canal.
  • C. reservoirType
    Indicates the specific kind or classification of a reservoir associated with an entity.
  • D. connectsUnder
    Indicates that one entity forms a connection to another entity by passing beneath or under it.
  • E. hasMajorReservoir
    Indicates that an entity possesses or is associated with a primary or significant reservoir (such as a large storage or accumulation of a resource).
  • F. None of above. chosen

Provenance (5 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_69a88aa51b388190949868ec9766e587 completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abc0670ce48190b98814064bff0517 completed March 7, 2026, 6:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69af1f74880481908ffd16a25792f013 completed March 9, 2026, 7:28 p.m.
PD Predicate disambiguation batch_69abbdadbb0c8190b3a1ede31b8acbfa completed March 7, 2026, 5:54 a.m.
PDg Predicate description generation batch_69abbe4252688190944491a450383450 completed March 7, 2026, 5:57 a.m.
Created at: March 4, 2026, 7:47 p.m.