Triple

T37491380
Position Surface form Disambiguated ID Type / Status
Subject 320 Park Avenue E931695 entity
Predicate isInRealEstateMarket P16332 FINISHED
Object Manhattan Class A office market
The Manhattan Class A office market comprises the highest-quality, premium office buildings in Manhattan, typically featuring prime locations, modern amenities, and top-tier tenants.
 E261909 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: Manhattan Class A office market | Statement: [320 Park Avenue, isInRealEstateMarket, Manhattan Class A office market]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Manhattan Class A office market
Triple: [320 Park Avenue, isInRealEstateMarket, Manhattan Class A office market]
Generated description
The Manhattan Class A office market comprises the highest-quality, premium office buildings in Manhattan, typically featuring prime locations, modern amenities, and top-tier tenants.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: isInRealEstateMarket
Context triple: [320 Park Avenue, isInRealEstateMarket, Manhattan Class A office market]
  • A. realEstate
    Indicates a relationship where an entity owns, manages, or is otherwise associated with real property such as land or buildings.
  • B. propertyMarket chosen
    Indicates a relationship where real estate or properties are being offered, traded, or evaluated within a market context.
  • C. realEstateMarketSegment
    Indicates the specific portion or category of the real estate market to which a property, transaction, or activity belongs (e.g., by price range, property type, or target buyer group).
  • D. realEstateDemand
    Indicates the level or presence of interest and desire among potential buyers or renters for a particular piece of real estate.
  • E. realEstateInterestsThrough
    Indicates that one party holds or exercises real estate interests indirectly through another entity, arrangement, or intermediary.
  • F. None of above.

Provenance (6 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_69f76ec457a4819094eeb3aed9baac11 completed May 3, 2026, 3:50 p.m.
NER Named-entity recognition batch_69fba68077788190b311e027435fcf87 completed May 6, 2026, 8:37 p.m.
NED1 Entity disambiguation (via context triple) batch_6a408c48a47c819090223d8014e32773 completed June 28, 2026, 2:51 a.m.
NEDg Description generation batch_6a408dcfa3d88190b70579dceeaf8eb7 completed June 28, 2026, 2:58 a.m.
NED2 Entity disambiguation (via description) batch_6a408e97e47c81909494b24e0e064f6f completed June 28, 2026, 3:01 a.m.
PD Predicate disambiguation batch_69fba34c65ac8190b298f0f00d1dcc0e completed May 6, 2026, 8:23 p.m.
Created at: May 3, 2026, 4:17 p.m.