Triple

T3182987
Position Surface form Disambiguated ID Type / Status
Subject St. George's, Grenada E66633 entity
Predicate hasLandmark P105 FINISHED
Object Sendall Tunnel
Sendall Tunnel is a historic stone roadway tunnel in St. George's, Grenada, that connects the town’s harbor area with its city center and is a notable local landmark.
 E333619 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: Sendall Tunnel | Statement: [St. George's, Grenada, hasLandmark, Sendall Tunnel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sendall Tunnel
Context triple: [St. George's, Grenada, hasLandmark, Sendall Tunnel]
  • A. TUN
    TUN is the three-letter ISO 3166-1 alpha-3 country code assigned to Tunisia.
  • B. Tunnel Log
    Tunnel Log is a fallen giant sequoia in Sequoia National Park that has been hollowed to allow cars to drive through its trunk, making it a popular roadside attraction.
  • C. Teredo
    Teredo is a tunneling protocol that enables IPv6 connectivity for devices on IPv4 networks, particularly those behind NAT.
  • D. Tunnel No. 2
    Tunnel No. 2 is one of New York City’s major water distribution tunnels that helps convey drinking water from upstate reservoirs to the city’s boroughs.
  • E. Tunnel No. 1
    Tunnel No. 1 is a major water-supply tunnel that forms part of New York City’s underground distribution system.
  • 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: Sendall Tunnel
Triple: [St. George's, Grenada, hasLandmark, Sendall Tunnel]
Generated description
Sendall Tunnel is a historic stone roadway tunnel in St. George's, Grenada, that connects the town’s harbor area with its city center and is a notable local landmark.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sendall Tunnel
Target entity description: Sendall Tunnel is a historic stone roadway tunnel in St. George's, Grenada, that connects the town’s harbor area with its city center and is a notable local landmark.
  • A. TUN
    TUN is the three-letter ISO 3166-1 alpha-3 country code assigned to Tunisia.
  • B. Tunnel Log
    Tunnel Log is a fallen giant sequoia in Sequoia National Park that has been hollowed to allow cars to drive through its trunk, making it a popular roadside attraction.
  • C. Teredo
    Teredo is a tunneling protocol that enables IPv6 connectivity for devices on IPv4 networks, particularly those behind NAT.
  • D. Tunnel No. 2
    Tunnel No. 2 is one of New York City’s major water distribution tunnels that helps convey drinking water from upstate reservoirs to the city’s boroughs.
  • E. Tunnel No. 1
    Tunnel No. 1 is a major water-supply tunnel that forms part of New York City’s underground distribution system.
  • 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_69ad8587c1bc8190a2595f2c22ee1001 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada6bea1788190bbce7cb52f8e72e8 completed March 8, 2026, 4:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69b2360079e4819085ee8b6553e3da02 completed March 12, 2026, 3:41 a.m.
NEDg Description generation batch_69b2372b4e888190b75235355b05a0ee completed March 12, 2026, 3:46 a.m.
NED2 Entity disambiguation (via description) batch_69b237927cf08190a21396a523f70dc9 completed March 12, 2026, 3:48 a.m.
Created at: March 8, 2026, 3:06 p.m.