Triple

T13252800
Position Surface form Disambiguated ID Type / Status
Subject Fulwell railway station E315576 entity
Predicate stationCode P1289 FINISHED
Object FLW
FLW is the National Rail station code for Fulwell railway station in London, England.
E1031048 NE FINISHED

How this triple was built (4 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: FLW | Statement: [Fulwell railway station, stationCode, FLW]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: FLW
Context triple: [Fulwell railway station, stationCode, FLW]
  • A. FLW
    FLW is the common abbreviation for Fort Leonard Wood, a major U.S. Army training installation located in Missouri.
  • B. FLW
    FLW is the three-letter IATA airport code for Flores Airport, which serves Flores Island in Portugal’s Azores archipelago.
  • C. Offshore Angler
    Offshore Angler is a Bass Pro Shops private-label brand specializing in saltwater fishing gear, tackle, and apparel.
  • D. Fishing Derby
    Fishing Derby is an early Atari 2600 video game designed by David Crane in which two players compete to catch fish while avoiding sharks.
  • E. White Marlin Open fishing tournament
    The White Marlin Open fishing tournament is one of the world’s largest and most prestigious billfish tournaments, drawing thousands of anglers and spectators each year to Ocean City, Maryland.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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: FLW
Triple: [Fulwell railway station, stationCode, FLW]
Generated description
FLW is the National Rail station code for Fulwell railway station in London, England.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: FLW
Target entity description: FLW is the National Rail station code for Fulwell railway station in London, England.
  • A. FLW
    FLW is the common abbreviation for Fort Leonard Wood, a major U.S. Army training installation located in Missouri.
  • B. FLW
    FLW is the three-letter IATA airport code for Flores Airport, which serves Flores Island in Portugal’s Azores archipelago.
  • C. Offshore Angler
    Offshore Angler is a Bass Pro Shops private-label brand specializing in saltwater fishing gear, tackle, and apparel.
  • D. Fishing Derby
    Fishing Derby is an early Atari 2600 video game designed by David Crane in which two players compete to catch fish while avoiding sharks.
  • E. White Marlin Open fishing tournament
    The White Marlin Open fishing tournament is one of the world’s largest and most prestigious billfish tournaments, drawing thousands of anglers and spectators each year to Ocean City, Maryland.
  • 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_69d806b1072881909e46bd212259c5f0 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98f73423c8190932a9edac56df383 completed April 11, 2026, 12:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69f70a3b8ca48190863aff25f12d0e7e completed May 3, 2026, 8:41 a.m.
NEDg Description generation batch_69f70b37ebe081909ed2ae0f42ccad2d completed May 3, 2026, 8:45 a.m.
NED2 Entity disambiguation (via description) batch_69f70ca343f08190b6484f464ed40810 completed May 3, 2026, 8:51 a.m.
Created at: April 9, 2026, 9:24 p.m.