Triple

T17806151
Position Surface form Disambiguated ID Type / Status
Subject Hessa Street E444562 entity
Predicate intersectsWith P13379 FINISHED
Object E311
E311, also known as Sheikh Mohammed Bin Zayed Road, is a major multi-lane highway in the United Arab Emirates that runs parallel to E11 and connects several key emirates.
E1288511 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: E311 | Statement: [Hessa Street, intersectsWith, E311]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: E311
Context triple: [Hessa Street, intersectsWith, E311]
  • A. E313
    E313 is a major Belgian motorway connecting Antwerp with Liège and serving as a key east–west transport corridor through the Limburg region.
  • B. E21
    E21 is the internal designation for the first generation of the BMW 3 Series compact executive car, produced in the 1970s and early 1980s.
  • C. E35
    E35 is a major north–south European route running from Amsterdam in the Netherlands to Rome in Italy, passing through Germany and Switzerland.
  • D. E12
    E12 is a European route that forms part of the international E-road network, connecting Finland with Sweden and Norway across the Nordic region.
  • E. E163
    E163 is a New York City Fire Department engine company that provides firefighting and emergency response services within its assigned area.
  • 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: E311
Triple: [Hessa Street, intersectsWith, E311]
Generated description
E311, also known as Sheikh Mohammed Bin Zayed Road, is a major multi-lane highway in the United Arab Emirates that runs parallel to E11 and connects several key emirates.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: E311
Target entity description: E311, also known as Sheikh Mohammed Bin Zayed Road, is a major multi-lane highway in the United Arab Emirates that runs parallel to E11 and connects several key emirates.
  • A. E313
    E313 is a major Belgian motorway connecting Antwerp with Liège and serving as a key east–west transport corridor through the Limburg region.
  • B. E21
    E21 is the internal designation for the first generation of the BMW 3 Series compact executive car, produced in the 1970s and early 1980s.
  • C. E35
    E35 is a major north–south European route running from Amsterdam in the Netherlands to Rome in Italy, passing through Germany and Switzerland.
  • D. E12
    E12 is a European route that forms part of the international E-road network, connecting Finland with Sweden and Norway across the Nordic region.
  • E. E163
    E163 is a New York City Fire Department engine company that provides firefighting and emergency response services within its assigned area.
  • 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_69d8b9efe370819095cd219b143ae727 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e488044cdc8190a09a2265c8a86475 completed April 19, 2026, 7:45 a.m.
NED1 Entity disambiguation (via context triple) batch_6a02f8452bc08190b25bdc91f3736e86 completed May 12, 2026, 9:52 a.m.
NEDg Description generation batch_6a02f9d944b8819095b6f9371f0f31bc completed May 12, 2026, 9:58 a.m.
NED2 Entity disambiguation (via description) batch_6a02fac96df48190884a8bc8517fbee7 completed May 12, 2026, 10:02 a.m.
Created at: April 10, 2026, 10:14 a.m.