Triple
T18635341
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Libérat Mfumukeko |
E455531
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object |
Libérat
Libérat is the given name of Libérat Mfumukeko, a Burundian diplomat and former Secretary General of the East African Community.
|
E1334415
|
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: Libérat | Statement: [Libérat Mfumukeko, givenName, Libérat]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Libérat Context triple: [Libérat Mfumukeko, givenName, Libérat]
-
A.
Libera
Libera is a volunteer-run, community-focused IRC network that hosts real-time discussions for free and open-source software projects and related communities.
-
B.
Libera
Libera is an ancient Roman goddess associated with fertility, wine, and freedom, often worshipped alongside Liber and Ceres.
-
C.
Liber
Liber is an ancient Roman god associated with viticulture, fertility, and freedom, often identified with the Greek god Dionysus.
-
D.
Liberté
Liberté is a celebrated World War II-era poem by French surrealist Paul Éluard, renowned as a powerful ode to freedom and resistance.
-
E.
Liberté
Liberté is a Paris Métro station in the commune of Charenton-le-Pont, serving Line 8 near the southeastern edge of the city.
- 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: Libérat Triple: [Libérat Mfumukeko, givenName, Libérat]
Generated description
Libérat is the given name of Libérat Mfumukeko, a Burundian diplomat and former Secretary General of the East African Community.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Libérat Target entity description: Libérat is the given name of Libérat Mfumukeko, a Burundian diplomat and former Secretary General of the East African Community.
-
A.
Libera
Libera is a volunteer-run, community-focused IRC network that hosts real-time discussions for free and open-source software projects and related communities.
-
B.
Libera
Libera is an ancient Roman goddess associated with fertility, wine, and freedom, often worshipped alongside Liber and Ceres.
-
C.
Liber
Liber is an ancient Roman god associated with viticulture, fertility, and freedom, often identified with the Greek god Dionysus.
-
D.
Liberté
Liberté is a Paris Métro station in the commune of Charenton-le-Pont, serving Line 8 near the southeastern edge of the city.
-
E.
Liberté
Liberté is a studio album by American rock band The Doobie Brothers, released in 2021 and marking one of their later-career returns to recording new material.
- 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_69d8d38cc7948190a55ea64e5638994e |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e54fc80b308190932303231524d372 |
completed | April 19, 2026, 9:57 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a050d8039f481909ffe9d62afbb2a23 |
completed | May 13, 2026, 11:47 p.m. |
| NEDg | Description generation | batch_6a050df74ca08190a7554396e052b702 |
completed | May 13, 2026, 11:49 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a050ecc33e48190bc28430a6a771492 |
completed | May 13, 2026, 11:52 p.m. |
Created at: April 10, 2026, 11:46 a.m.