Triple

T25715411

Position	Surface form	Disambiguated ID	Type / Status
Subject	London–Tokyo	`E644848`	entity
Predicate	servedByAirportPair	`P175948`	FINISHED
Object	London Heathrow Airport – Tokyo Haneda Airport London Heathrow Airport – Tokyo Haneda Airport is a major intercontinental air route linking the primary international airports of London and Tokyo.	`E644848`	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: London Heathrow Airport – Tokyo Haneda Airport | Statement: [London–Tokyo, servedByAirportPair, London Heathrow Airport – Tokyo Haneda Airport]

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: London Heathrow Airport – Tokyo Haneda Airport
Triple: [London–Tokyo, servedByAirportPair, London Heathrow Airport – Tokyo Haneda Airport]

Generated description

London Heathrow Airport – Tokyo Haneda Airport is a major intercontinental air route linking the primary international airports of London and Tokyo.

PD Predicate disambiguation gpt-5-mini-2025-08-07

Target predicate: servedByAirportPair
Context triple: [London–Tokyo, servedByAirportPair, London Heathrow Airport – Tokyo Haneda Airport]

A. servedByCityPair
Indicates that a service (such as a route or connection) is provided between a specific pair of cities.
B. servedByAirportInOriginCity
Indicates that the origin city of a trip or route is served by a particular airport.
C. associatedAirportServes
Indicates that a given airport provides service to, or is used by, the associated entity (such as a city, region, or facility).
D. airportCodePair
Indicates a relationship between two entities where each is associated with a specific airport code, typically representing a pair of airports linked in some context such as a route or connection.
E. servesAirport
Indicates that a transportation service or route provides access to and operates for a particular airport.
F. None of above. chosen

Provenance (7 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_69e77e8476fc8190bd5e9d05b89fad0a`	completed	April 21, 2026, 1:41 p.m.
NER	Named-entity recognition	`batch_69f6db3606808190a80c6e9f5da5b33e`	completed	May 3, 2026, 5:20 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a10c176e3b08190ae6c5e67503f3536`	completed	May 22, 2026, 8:49 p.m.
NEDg	Description generation	`batch_6a10c25f38548190a7487c7cb829bce0`	completed	May 22, 2026, 8:53 p.m.
NED2	Entity disambiguation (via description)	`batch_6a10c4dc54f481909f2e06eaa2d15d43`	completed	May 22, 2026, 9:04 p.m.
PD	Predicate disambiguation	`batch_69f6d82adfa481908a5e196d2e18c73f`	completed	May 3, 2026, 5:07 a.m.
PDg	Predicate description generation	`batch_69f6db1bc348819097c844f76e2fa4fe`	completed	May 3, 2026, 5:20 a.m.

Created at: April 21, 2026, 9:40 p.m.