Triple

T9233219
Position Surface form Disambiguated ID Type / Status
Subject SBRY E221872 entity
Predicate exchangeMic P2798 FINISHED
Object XLON
XLON is the Market Identifier Code for the London Stock Exchange, one of the world’s largest and most prominent stock markets.
 E786154 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: XLON | Statement: [SBRY, exchangeMic, XLON]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: XLON
Context triple: [SBRY, exchangeMic, XLON]
  • A. HXL
    HXL (Humanitarian Exchange Language) is a lightweight data standard designed to improve the interoperability, quality, and rapid sharing of humanitarian data across organizations and crises.
  • B. XRL
    XRL is a high-speed rail line connecting Guangzhou, Shenzhen, and Hong Kong, forming a key part of China’s national high-speed railway network.
  • C. Xelb
    Xelb is the former Arabic name for the Portuguese city of Silves, a historically significant town in the Algarve region.
  • D. LX
    LX is the second-generation Holden Torana series produced in the mid-1970s, notable for introducing the A9X performance package and being a popular Australian mid-size car in both road and racing forms.
  • E. LX
    LX is the IATA airline designator used to identify Swiss International Air Lines on tickets, timetables, and flight numbers.
  • 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: XLON
Triple: [SBRY, exchangeMic, XLON]
Generated description
XLON is the Market Identifier Code for the London Stock Exchange, one of the world’s largest and most prominent stock markets.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: XLON
Target entity description: XLON is the Market Identifier Code for the London Stock Exchange, one of the world’s largest and most prominent stock markets.
  • A. HXL
    HXL (Humanitarian Exchange Language) is a lightweight data standard designed to improve the interoperability, quality, and rapid sharing of humanitarian data across organizations and crises.
  • B. XRL
    XRL is a high-speed rail line connecting Guangzhou, Shenzhen, and Hong Kong, forming a key part of China’s national high-speed railway network.
  • C. Xelb
    Xelb is the former Arabic name for the Portuguese city of Silves, a historically significant town in the Algarve region.
  • D. LX
    LX is the second-generation Holden Torana series produced in the mid-1970s, notable for introducing the A9X performance package and being a popular Australian mid-size car in both road and racing forms.
  • E. LX
    LX is the IATA airline designator used to identify Swiss International Air Lines on tickets, timetables, and flight numbers.
  • 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_69ca83ed628c8190bc02d641e57f097f completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69ccee1baa3c8190870d1e850ccab1e0 completed April 1, 2026, 10:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69d077bb5b10819083fd2de3ed7d69a4 completed April 4, 2026, 2:30 a.m.
NEDg Description generation batch_69d079227348819083cc2c1bb36831f0 completed April 4, 2026, 2:36 a.m.
NED2 Entity disambiguation (via description) batch_69d07980eb1481909450ec1e6537587f completed April 4, 2026, 2:37 a.m.
Created at: March 30, 2026, 7:29 p.m.