Triple
T2534419
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oyo |
E56234
|
entity |
| Predicate | militaryInstitution |
P4889
|
FINISHED |
| Object |
Eso Ikoyi
Eso Ikoyi were an elite warrior caste of the Oyo Empire in Yorubaland, renowned for their strict code of honor, bravery, and key role in the empire’s military campaigns.
|
E274609
|
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: Eso Ikoyi | Statement: [Oyo, militaryInstitution, Eso Ikoyi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eso Ikoyi Context triple: [Oyo, militaryInstitution, Eso Ikoyi]
-
A.
Lekki
Lekki is a fictional companion mascot character associated with Nokki, likely designed as a cute, supportive sidekick figure.
-
B.
Lekki
Lekki is the official mascot character created for the XVIII Olympic Winter Games.
-
C.
Harpurhey
Harpurhey is an inner-city district of Manchester, England, known for its dense residential areas and local shopping precincts.
-
D.
Ijebu-Ode
Ijebu-Ode is a historic Yoruba town in southwestern Nigeria known as a traditional political and cultural center of the Ijebu people.
-
E.
Ado-Ekiti
Ado-Ekiti is the capital and largest city of Ekiti State in southwestern Nigeria, known as an administrative, educational, and commercial center for the surrounding region.
- 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: Eso Ikoyi Triple: [Oyo, militaryInstitution, Eso Ikoyi]
Generated description
Eso Ikoyi were an elite warrior caste of the Oyo Empire in Yorubaland, renowned for their strict code of honor, bravery, and key role in the empire’s military campaigns.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Eso Ikoyi Target entity description: Eso Ikoyi were an elite warrior caste of the Oyo Empire in Yorubaland, renowned for their strict code of honor, bravery, and key role in the empire’s military campaigns.
-
A.
Lekki
Lekki is a fictional companion mascot character associated with Nokki, likely designed as a cute, supportive sidekick figure.
-
B.
Lekki
Lekki is the official mascot character created for the XVIII Olympic Winter Games.
-
C.
Harpurhey
Harpurhey is an inner-city district of Manchester, England, known for its dense residential areas and local shopping precincts.
-
D.
Ijebu-Ode
Ijebu-Ode is a historic Yoruba town in southwestern Nigeria known as a traditional political and cultural center of the Ijebu people.
-
E.
Ado-Ekiti
Ado-Ekiti is the capital and largest city of Ekiti State in southwestern Nigeria, known as an administrative, educational, and commercial center for the surrounding region.
- 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_69ab4a49b6508190bc467fbef4bac334 |
completed | March 6, 2026, 9:42 p.m. |
| NER | Named-entity recognition | batch_69abd27c8650819080005869789b802c |
completed | March 7, 2026, 7:23 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69af2bbc416c81908774782420b54664 |
completed | March 9, 2026, 8:21 p.m. |
| NEDg | Description generation | batch_69af4c5e49dc8190920612a8b0f5b3f7 |
completed | March 9, 2026, 10:40 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69af4cd3bcc8819091589f0aa27ddc5d |
completed | March 9, 2026, 10:42 p.m. |
Created at: March 6, 2026, 9:47 p.m.