Triple

T14797816
Position Surface form Disambiguated ID Type / Status
Subject King Agaja E347824 entity
Predicate expandedTerritoryTo P18876 FINISHED
Object Allada
Allada was a precolonial West African kingdom in present-day Benin that became an important Aja state and regional trading center before being absorbed by the expanding Kingdom of Dahomey.
 E1122582 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: Allada | Statement: [King Agaja, expandedTerritoryTo, Allada]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Allada
Context triple: [King Agaja, expandedTerritoryTo, Allada]
  • A. Alawa
    Alawa is a residential suburb in the northern part of Darwin, in Australia's Northern Territory.
  • B. Aldah
    Aldah is a figure from Islamic tradition known as a sibling of Abida, mentioned in genealogical accounts of early Arab lineages.
  • C. Aldith
    Aldith is a fictional character appearing in Ellis Peters' medieval mystery novel "Monk’s Hood."
  • D. Algedi
    Algedi is a traditional name for Alpha Capricorni, a multiple star system in the constellation Capricornus visible to the naked eye.
  • E. Andoolo
    Andoolo is a small town that serves as an administrative center in the Indonesian province of Southeast Sulawesi.
  • 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: Allada
Triple: [King Agaja, expandedTerritoryTo, Allada]
Generated description
Allada was a precolonial West African kingdom in present-day Benin that became an important Aja state and regional trading center before being absorbed by the expanding Kingdom of Dahomey.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Allada
Target entity description: Allada was a precolonial West African kingdom in present-day Benin that became an important Aja state and regional trading center before being absorbed by the expanding Kingdom of Dahomey.
  • A. Alawa
    Alawa is a residential suburb in the northern part of Darwin, in Australia's Northern Territory.
  • B. Aldah
    Aldah is a figure from Islamic tradition known as a sibling of Abida, mentioned in genealogical accounts of early Arab lineages.
  • C. Aldith
    Aldith is a fictional character appearing in Ellis Peters' medieval mystery novel "Monk’s Hood."
  • D. Algedi
    Algedi is a traditional name for Alpha Capricorni, a multiple star system in the constellation Capricornus visible to the naked eye.
  • E. Andoolo
    Andoolo is a small town that serves as an administrative center in the Indonesian province of Southeast Sulawesi.
  • 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_69d822ea8b7c819097dfadf3d45545e6 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69decd6131f08190885f1d27b4bfac7a completed April 14, 2026, 11:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe389183a881908e6af44b71f81ace completed May 8, 2026, 7:25 p.m.
NEDg Description generation batch_69fe56cb6bb881909614b3667c0f2448 completed May 8, 2026, 9:34 p.m.
NED2 Entity disambiguation (via description) batch_69fe575e6cdc8190b1f22f8e8110e64d completed May 8, 2026, 9:36 p.m.
Created at: April 10, 2026, 1:31 a.m.