Triple

T14562349
Position Surface form Disambiguated ID Type / Status
Subject Battle of Tondibi E341697 entity
Predicate locatedIn P40 FINISHED
Object Tondibi
Tondibi is a historic site in present-day Mali known as the location of a decisive 1591 battle that led to the fall of the Songhai Empire.
 E1106685 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: Tondibi | Statement: [Battle of Tondibi, locatedIn, Tondibi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tondibi
Context triple: [Battle of Tondibi, locatedIn, Tondibi]
  • A. Garuwa
    Garuwa is the Indigenous name used by local Aboriginal people for Australia’s Karuah River.
  • B. Ojowo
    Ojowo is a town within the Ijebu North area of Ogun State in southwestern Nigeria.
  • C. Ngoumbi
    Ngoumbi is an alternative name for the Kombe people, an ethnic group of Central Africa.
  • D. Garki
    Garki is a prominent administrative and commercial district in Nigeria’s capital city, Abuja, housing numerous government offices, businesses, and residential areas.
  • E. Barawa
    Barawa is a West Chadic language spoken in parts of Nigeria, belonging to the Afroasiatic language family.
  • 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: Tondibi
Triple: [Battle of Tondibi, locatedIn, Tondibi]
Generated description
Tondibi is a historic site in present-day Mali known as the location of a decisive 1591 battle that led to the fall of the Songhai Empire.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tondibi
Target entity description: Tondibi is a historic site in present-day Mali known as the location of a decisive 1591 battle that led to the fall of the Songhai Empire.
  • A. Garuwa
    Garuwa is the Indigenous name used by local Aboriginal people for Australia’s Karuah River.
  • B. Ojowo
    Ojowo is a town within the Ijebu North area of Ogun State in southwestern Nigeria.
  • C. Ngoumbi
    Ngoumbi is an alternative name for the Kombe people, an ethnic group of Central Africa.
  • D. Garki
    Garki is a prominent administrative and commercial district in Nigeria’s capital city, Abuja, housing numerous government offices, businesses, and residential areas.
  • E. Barawa
    Barawa is a West Chadic language spoken in parts of Nigeria, belonging to the Afroasiatic language family.
  • 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_69d822dcc6248190bed689984bceb0e2 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb38afa8881909c9151b7620949ae completed April 14, 2026, 9:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd8ac294748190a4bfeed8c5fd9e94 completed May 8, 2026, 7:03 a.m.
NEDg Description generation batch_69fd8c3678048190a23b509e963c1ade completed May 8, 2026, 7:09 a.m.
NED2 Entity disambiguation (via description) batch_69fd8d609684819090a9c3f2304f4a6a completed May 8, 2026, 7:14 a.m.
Created at: April 10, 2026, 1:23 a.m.