Triple

T1072357
Position Surface form Disambiguated ID Type / Status
Subject Louis Kahn E23357 entity
Predicate notableWork P4 FINISHED
Object Fisher House E85300 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: Fisher House | Statement: [Louis Kahn, notableWork, Fisher House]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fisher House
Context triple: [Louis Kahn, notableWork, Fisher House]
  • A. Fisher House Foundation
    Fisher House Foundation is a nonprofit organization that provides free lodging and support to families of hospitalized military service members and veterans near major military and VA medical centers.
  • B. Huntington Place
    Huntington Place is a major convention center in downtown Detroit, Michigan, known for hosting large-scale events and trade shows.
  • C. Hope Lodge
    Hope Lodge is a network of free lodging facilities that provide cancer patients and their caregivers with a supportive place to stay during treatment away from home.
  • D. Haas House chosen
    Haas House is a postmodern commercial and office building in Vienna, Austria, renowned for its striking contemporary design and controversial contrast with the historic St. Stephen's Cathedral opposite it.
  • E. Hillwood
    Hillwood is a real estate development company known for large-scale industrial, commercial, and mixed-use projects across the United States.
  • 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_69a493ee1f908190992b5f0d1b04459b completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b9296c5c8190a3060fbfdf24f029 completed March 1, 2026, 10:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac42a70ab88190ba0f0a62b19af871 completed March 7, 2026, 3:22 p.m.
Created at: March 1, 2026, 7:42 p.m.