Triple

T6996233
Position Surface form Disambiguated ID Type / Status
Subject Avikam language E162221 entity
Predicate hasAlternativeName P39 FINISHED
Object Avikam
Avikam is a Kwa language spoken by the Avikam people in southern Côte d'Ivoire.
 E634471 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: Avikam | Statement: [Avikam language, hasAlternativeName, Avikam]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Avikam
Context triple: [Avikam language, hasAlternativeName, Avikam]
  • A. Akhami
    Akhami is an alternative name for the Achomi language, an Iranian language spoken primarily by communities in southern Iran and the Persian Gulf region.
  • B. Ein Avdat
    Ein Avdat is a dramatic desert canyon and oasis in southern Israel known for its steep cliffs, springs, and hiking trails.
  • C. Achziv
    Achziv is a small coastal area in northern Israel known for its beaches, national park, and archaeological remains of ancient settlements.
  • D. Savyon
    Savyon is an affluent residential town in central Israel known for its spacious villas, high standard of living, and proximity to Tel Aviv.
  • E. Aykah
    Aykah is a community mentioned in Islamic tradition as the people to whom the prophet Shu'ayb was sent, known for their wrongdoing and subsequent divine punishment.
  • 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: Avikam
Triple: [Avikam language, hasAlternativeName, Avikam]
Generated description
Avikam is a Kwa language spoken by the Avikam people in southern Côte d'Ivoire.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Avikam
Target entity description: Avikam is a Kwa language spoken by the Avikam people in southern Côte d'Ivoire.
  • A. Akhami
    Akhami is an alternative name for the Achomi language, an Iranian language spoken primarily by communities in southern Iran and the Persian Gulf region.
  • B. Ein Avdat
    Ein Avdat is a dramatic desert canyon and oasis in southern Israel known for its steep cliffs, springs, and hiking trails.
  • C. Achziv
    Achziv is a small coastal area in northern Israel known for its beaches, national park, and archaeological remains of ancient settlements.
  • D. Savyon
    Savyon is an affluent residential town in central Israel known for its spacious villas, high standard of living, and proximity to Tel Aviv.
  • E. Aykah
    Aykah is a community mentioned in Islamic tradition as the people to whom the prophet Shu'ayb was sent, known for their wrongdoing and subsequent divine punishment.
  • 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_69c68857ffc08190857dc62cd5253777 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6dbedafa48190af0d2b47e3a1e17e completed March 27, 2026, 7:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69c76a1fa11481908450978acc1e0913 completed March 28, 2026, 5:41 a.m.
NEDg Description generation batch_69c76b84f5688190a0aef7cd8695c6b0 completed March 28, 2026, 5:47 a.m.
NED2 Entity disambiguation (via description) batch_69c76be95ecc8190a57ff197f236d434 completed March 28, 2026, 5:49 a.m.
Created at: March 27, 2026, 2:32 p.m.