Triple

T20657554
Position Surface form Disambiguated ID Type / Status
Subject Lubombo Region E507666 entity
Predicate hasCapital P204 FINISHED
Object Siteki
Siteki is a town in eastern Eswatini that serves as the administrative and commercial center of the Lubombo Region.
 E1442719 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: Siteki | Statement: [Lubombo Region, hasCapital, Siteki]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Siteki
Context triple: [Lubombo Region, hasCapital, Siteki]
  • A. Teke
    Teke is a Bantu language spoken primarily in the Republic of the Congo and neighboring Central African regions by the Teke people.
  • B. Teke
    Teke are a prominent Turkmen tribal group historically known for their influence in Central Asia and their famed Akhal-Teke horses.
  • C. Seke
    Seke is an Oceanic language spoken by communities on Pentecost Island in Vanuatu.
  • D. Sikaiana
    Sikaiana is a small, remote Polynesian atoll in the Solomon Islands whose people and culture are part of the Polynesian outlier communities in Melanesia.
  • E. Sekani
    The Sekani are an Athabaskan-speaking Indigenous people of north-central British Columbia, Canada, traditionally known as semi-nomadic hunters and fishers of the interior plateau and subarctic regions.
  • 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: Siteki
Triple: [Lubombo Region, hasCapital, Siteki]
Generated description
Siteki is a town in eastern Eswatini that serves as the administrative and commercial center of the Lubombo Region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Siteki
Target entity description: Siteki is a town in eastern Eswatini that serves as the administrative and commercial center of the Lubombo Region.
  • A. Teke
    Teke is a Bantu language spoken primarily in the Republic of the Congo and neighboring Central African regions by the Teke people.
  • B. Teke
    Teke are a prominent Turkmen tribal group historically known for their influence in Central Asia and their famed Akhal-Teke horses.
  • C. Seke
    Seke is an Oceanic language spoken by communities on Pentecost Island in Vanuatu.
  • D. Sikaiana
    Sikaiana is a small, remote Polynesian atoll in the Solomon Islands whose people and culture are part of the Polynesian outlier communities in Melanesia.
  • E. Sekani
    The Sekani are an Athabaskan-speaking Indigenous people of north-central British Columbia, Canada, traditionally known as semi-nomadic hunters and fishers of the interior plateau and subarctic regions.
  • 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_69e0b4bf58c081908e52a4500e03ff83 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6b2ee049081909904efe2dc683cd5 completed April 20, 2026, 11:12 p.m.
NED1 Entity disambiguation (via context triple) batch_6a08c5999180819091f3f1255b490150 completed May 16, 2026, 7:29 p.m.
NEDg Description generation batch_6a08c6b50ea8819083ff85b85b2b6082 completed May 16, 2026, 7:34 p.m.
NED2 Entity disambiguation (via description) batch_6a08c7bf78b48190936455734ecf055d completed May 16, 2026, 7:38 p.m.
Created at: April 16, 2026, 11:43 a.m.