Triple

T22472644
Position Surface form Disambiguated ID Type / Status
Subject Somers Town E555542 entity
Predicate locatedNear P294 FINISHED
Object Landport
Landport is a district of Portsmouth, England, known historically as a densely populated residential and commercial area just outside the old city fortifications.
 E535686 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: Landport | Statement: [Somers Town, locatedNear, Landport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Landport
Context triple: [Somers Town, locatedNear, Landport]
  • A. Landport
    Landport is a historic inner-city district of Portsmouth, England, known for its dense urban character and proximity to the city centre on Portsea Island.
  • B. Portlock
    Portlock is an affluent residential neighborhood in East Honolulu, Hawaii, known for its oceanfront homes and scenic coastal views.
  • C. Portbury
    Portbury is a small village and civil parish in North Somerset, England, situated near the River Avon and close to the Port of Bristol.
  • D. Milport
    Milport is a fictional British parliamentary constituency featured in Patrick O’Brian’s Aubrey–Maturin historical naval novels.
  • E. Portington
    Portington is a small rural settlement located within the Howdenshire area of the East Riding of Yorkshire, England.
  • 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: Landport
Triple: [Somers Town, locatedNear, Landport]
Generated description
Landport is a district of Portsmouth, England, known historically as a densely populated residential and commercial area just outside the old city fortifications.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Landport
Target entity description: Landport is a district of Portsmouth, England, known historically as a densely populated residential and commercial area just outside the old city fortifications.
  • A. Landport chosen
    Landport is a historic inner-city district of Portsmouth, England, known for its dense urban character and proximity to the city centre on Portsea Island.
  • B. Portlock
    Portlock is an affluent residential neighborhood in East Honolulu, Hawaii, known for its oceanfront homes and scenic coastal views.
  • C. Portbury
    Portbury is a small village and civil parish in North Somerset, England, situated near the River Avon and close to the Port of Bristol.
  • D. Milport
    Milport is a fictional British parliamentary constituency featured in Patrick O’Brian’s Aubrey–Maturin historical naval novels.
  • E. Portington
    Portington is a small rural settlement located within the Howdenshire area of the East Riding of Yorkshire, England.
  • F. None of above.

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_69e11e52c2048190952dc5df209b9bed completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15be2034c81909d1263f2ed114b46 completed April 29, 2026, 1:16 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b125b26008190a232bac277b253c5 completed May 18, 2026, 1:21 p.m.
NEDg Description generation batch_6a0b14b7acac819090bfd6144df84be6 completed May 18, 2026, 1:31 p.m.
NED2 Entity disambiguation (via description) batch_6a0b154f7e0c8190b0ca64d582982d62 completed May 18, 2026, 1:34 p.m.
Created at: April 16, 2026, 8:49 p.m.