Triple

T7156569
Position Surface form Disambiguated ID Type / Status
Subject باب المندب E166826 entity
Predicate يقع بين P75193 FINISHED
Object جيبوتي
جيبوتي دولة عربية صغيرة تقع في القرن الأفريقي على ساحل البحر الأحمر وخليج عدن، وتتميز بموقع استراتيجي مهم للتجارة العالمية والملاحة البحرية.
 E645726 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: جيبوتي | Statement: [باب المندب, يقع بين, جيبوتي]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: جيبوتي
Context triple: [باب المندب, يقع بين, جيبوتي]
  • A. Dumbéa
    Dumbéa is a suburban commune of Greater Nouméa in New Caledonia, known for its rapid urban growth and mix of residential areas and natural river valleys.
  • B. Djibloho
    Djibloho is a planned administrative capital city and province of Equatorial Guinea located in the mainland region of Río Muni.
  • C. Sué
    Sué is the Muisca sun god, a principal deity associated with light, warmth, and cosmic order in the mythology of the pre-Columbian Muisca people of the Colombian Andes.
  • D. Iéna
    Iéna is a Paris Métro station in the 16th arrondissement, located near landmarks such as the Palais de Tokyo and the Trocadéro.
  • E. Lamboya
    Lamboya is an Austronesian language spoken by the Lamboya people on the island of Sumba in eastern Indonesia.
  • 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: جيبوتي
Triple: [باب المندب, يقع بين, جيبوتي]
Generated description
جيبوتي دولة عربية صغيرة تقع في القرن الأفريقي على ساحل البحر الأحمر وخليج عدن، وتتميز بموقع استراتيجي مهم للتجارة العالمية والملاحة البحرية.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: جيبوتي
Target entity description: جيبوتي دولة عربية صغيرة تقع في القرن الأفريقي على ساحل البحر الأحمر وخليج عدن، وتتميز بموقع استراتيجي مهم للتجارة العالمية والملاحة البحرية.
  • A. Dumbéa
    Dumbéa is a suburban commune of Greater Nouméa in New Caledonia, known for its rapid urban growth and mix of residential areas and natural river valleys.
  • B. Djibloho
    Djibloho is a planned administrative capital city and province of Equatorial Guinea located in the mainland region of Río Muni.
  • C. Sué
    Sué is the Muisca sun god, a principal deity associated with light, warmth, and cosmic order in the mythology of the pre-Columbian Muisca people of the Colombian Andes.
  • D. Iéna
    Iéna is a Paris Métro station in the 16th arrondissement, located near landmarks such as the Palais de Tokyo and the Trocadéro.
  • E. Lamboya
    Lamboya is an Austronesian language spoken by the Lamboya people on the island of Sumba in eastern Indonesia.
  • 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_69c68887a5cc8190bec0ea96227164f7 completed March 27, 2026, 1:39 p.m.
NER Named-entity recognition batch_69c6e80dafdc8190b24863b83f084d12 completed March 27, 2026, 8:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7adb530388190b68fa05418d3e184 completed March 28, 2026, 10:30 a.m.
NEDg Description generation batch_69c7ae830c74819091d6d65ac6fba32b completed March 28, 2026, 10:33 a.m.
NED2 Entity disambiguation (via description) batch_69c7af1133b08190a32dccf82015c19e completed March 28, 2026, 10:36 a.m.
Created at: March 27, 2026, 2:47 p.m.