Triple

T6326037
Position Surface form Disambiguated ID Type / Status
Subject Ras Beirut E141864 entity
Predicate contains P35 FINISHED
Object Manara
Manara is a coastal neighborhood in Beirut, Lebanon, known for its seaside promenade and iconic lighthouse.
E583587 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: Manara | Statement: [Ras Beirut, contains, Manara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Manara
Context triple: [Ras Beirut, contains, Manara]
  • A. Al Hamra Tower
    Al Hamra Tower is a prominent skyscraper in Kuwait City known for its distinctive twisting design and status as one of the tallest buildings in Kuwait.
  • B. Milad Tower
    Milad Tower is a prominent multi-purpose telecommunications and observation tower in Tehran, Iran, and one of the tallest towers in the world.
  • C. Cairo Tower
    Cairo Tower is a prominent modernist concrete television and observation tower in central Cairo, renowned for its panoramic views over the city and the Nile.
  • D. Al Zaeem
    Al Zaeem is the famous Arabic nickname for Al Hilal SFC, one of Saudi Arabia’s most successful and popular football clubs.
  • E. Al Manhal
    Al Manhal is a bottled drinking water brand marketed in the Middle East under Nestlé Waters’ portfolio.
  • 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: Manara
Triple: [Ras Beirut, contains, Manara]
Generated description
Manara is a coastal neighborhood in Beirut, Lebanon, known for its seaside promenade and iconic lighthouse.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Manara
Target entity description: Manara is a coastal neighborhood in Beirut, Lebanon, known for its seaside promenade and iconic lighthouse.
  • A. Al Hamra Tower
    Al Hamra Tower is a prominent skyscraper in Kuwait City known for its distinctive twisting design and status as one of the tallest buildings in Kuwait.
  • B. Milad Tower
    Milad Tower is a prominent multi-purpose telecommunications and observation tower in Tehran, Iran, and one of the tallest towers in the world.
  • C. Cairo Tower
    Cairo Tower is a prominent modernist concrete television and observation tower in central Cairo, renowned for its panoramic views over the city and the Nile.
  • D. Al Zaeem
    Al Zaeem is the famous Arabic nickname for Al Hilal SFC, one of Saudi Arabia’s most successful and popular football clubs.
  • E. Al Manhal
    Al Manhal is a bottled drinking water brand marketed in the Middle East under Nestlé Waters’ portfolio.
  • 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_69c008d201748190917e69c41ba3f978 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c064e833a0819096000b47e776949d completed March 22, 2026, 9:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69c5e4960ac08190bcdebde8a607d2b5 completed March 27, 2026, 1:59 a.m.
NEDg Description generation batch_69c5e6a948c881909fa3d78408125c04 completed March 27, 2026, 2:08 a.m.
NED2 Entity disambiguation (via description) batch_69c5e713ea5c81908aeb6c5776f0ae10 completed March 27, 2026, 2:10 a.m.
Created at: March 22, 2026, 4:29 p.m.