Triple

T15989882
Position Surface form Disambiguated ID Type / Status
Subject Redfin E387794 entity
Predicate offersProduct P10882 FINISHED
Object Redfin Estimate E387794 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: Redfin Estimate | Statement: [Redfin, offersProduct, Redfin Estimate]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Redfin Estimate
Context triple: [Redfin, offersProduct, Redfin Estimate]
  • A. Zillow
    Zillow is a major U.S.-based online real estate marketplace that provides home listings, value estimates, and related housing data to buyers, sellers, and renters.
  • B. Redfin chosen
    Redfin is a technology-powered real estate brokerage and listings platform that enables users to buy, sell, and search for homes online.
  • C. Opendoor
    Opendoor is a U.S.-based real estate technology company that pioneered the iBuyer model, enabling homeowners to sell their homes online quickly for cash offers.
  • D. LendingTree
    LendingTree is an online lending marketplace that connects consumers with multiple lenders for mortgages, personal loans, credit cards, and other financial products.
  • E. OpenEEmeter
    OpenEEmeter is an open-source software toolkit that standardizes the measurement and verification of energy efficiency and demand flexibility impacts from building energy data.
  • 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_69d86daa562c81908aacc179c0fe8fb5 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e157829ec08190aa4a683e29a0148a completed April 16, 2026, 9:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffc3d2369081909efa2d4addf0cf2d completed May 9, 2026, 11:31 p.m.
Created at: April 10, 2026, 4:54 a.m.