Triple

T6875987
Position Surface form Disambiguated ID Type / Status
Subject NHS e‑Referral Service E158671 entity
Predicate hasAbbreviation P43 FINISHED
Object e-RS
e-RS is the abbreviation for the NHS e‑Referral Service, a digital system used in the UK to manage and book patient referrals electronically.
 E626397 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: e-RS | Statement: [NHS e‑Referral Service, hasAbbreviation, e-RS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: e-RS
Context triple: [NHS e‑Referral Service, hasAbbreviation, e-RS]
  • A. ER3
    ER3 is the IATA aircraft type code used to designate the Embraer ERJ 135 regional jet.
  • B. RSE
    RSE is the commonly used abbreviation for the Royal Society of Edinburgh, Scotland’s national academy of science and letters.
  • C. SRES
    SRES is the School of Resources and Environmental Science at Wuhan University, a faculty focused on education and research in natural resources, geography, and environmental science.
  • D. E-root
    E-root is one of the Internet’s authoritative DNS root servers, responsible for serving the root zone and directing queries to top-level domain name servers.
  • E. R.E.
    R.E. is the post-nominal abbreviation used by members of Denmark’s highest chivalric distinction, the Order of the Elephant.
  • 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: e-RS
Triple: [NHS e‑Referral Service, hasAbbreviation, e-RS]
Generated description
e-RS is the abbreviation for the NHS e‑Referral Service, a digital system used in the UK to manage and book patient referrals electronically.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: e-RS
Target entity description: e-RS is the abbreviation for the NHS e‑Referral Service, a digital system used in the UK to manage and book patient referrals electronically.
  • A. ER3
    ER3 is the IATA aircraft type code used to designate the Embraer ERJ 135 regional jet.
  • B. RSE
    RSE is the commonly used abbreviation for the Royal Society of Edinburgh, Scotland’s national academy of science and letters.
  • C. SRES
    SRES is the School of Resources and Environmental Science at Wuhan University, a faculty focused on education and research in natural resources, geography, and environmental science.
  • D. E-root
    E-root is one of the Internet’s authoritative DNS root servers, responsible for serving the root zone and directing queries to top-level domain name servers.
  • E. R.E.
    R.E. is the post-nominal abbreviation used by members of Denmark’s highest chivalric distinction, the Order of the Elephant.
  • 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_69c68832af1481908ce356e133ebaebe completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d8cb76108190a5136240ed85d900 completed March 27, 2026, 7:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69c742bd0bfc8190971aa9d8b7e6709d completed March 28, 2026, 2:53 a.m.
NEDg Description generation batch_69c74546fb048190924677a3805e4d70 completed March 28, 2026, 3:04 a.m.
NED2 Entity disambiguation (via description) batch_69c745df6de48190b4c50dcb1a5c0231 completed March 28, 2026, 3:07 a.m.
Created at: March 27, 2026, 2:22 p.m.