Triple
T13212754
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UFC 81 |
E314533
|
entity |
| Predicate | featuredFighter |
P101800
|
FINISHED |
| Object |
Gleison Tibau
Gleison Tibau is a Brazilian mixed martial artist best known for his long tenure as a lightweight competitor in the UFC.
|
E1026696
|
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: Gleison Tibau | Statement: [UFC 81, featuredFighter, Gleison Tibau]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gleison Tibau Context triple: [UFC 81, featuredFighter, Gleison Tibau]
-
A.
Leandro Barbosa
Leandro Barbosa is a Brazilian professional basketball player and NBA champion known for his speed and scoring ability, particularly during his tenure with the Phoenix Suns.
-
B.
Leandro Nunes
Leandro Nunes is a Brazilian jiu-jitsu black belt competitor and coach known within the grappling community for his technical skill and tournament performances.
-
C.
Guilherme Leal
Guilherme Leal is a Brazilian businessman, co-founder of the cosmetics company Natura, and a prominent environmental and social activist.
-
D.
Emanoel Araújo
Emanoel Araújo was a Brazilian artist, curator, and cultural leader renowned for his work in promoting Afro-Brazilian art and heritage.
-
E.
Thiago Teixeira
Thiago Teixeira is a technology entrepreneur best known as a co-founder of the data app development platform Streamlit.
- 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: Gleison Tibau Triple: [UFC 81, featuredFighter, Gleison Tibau]
Generated description
Gleison Tibau is a Brazilian mixed martial artist best known for his long tenure as a lightweight competitor in the UFC.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Gleison Tibau Target entity description: Gleison Tibau is a Brazilian mixed martial artist best known for his long tenure as a lightweight competitor in the UFC.
-
A.
Leandro Barbosa
Leandro Barbosa is a Brazilian professional basketball player and NBA champion known for his speed and scoring ability, particularly during his tenure with the Phoenix Suns.
-
B.
Leandro Nunes
Leandro Nunes is a Brazilian jiu-jitsu black belt competitor and coach known within the grappling community for his technical skill and tournament performances.
-
C.
Guilherme Leal
Guilherme Leal is a Brazilian businessman, co-founder of the cosmetics company Natura, and a prominent environmental and social activist.
-
D.
Emanoel Araújo
Emanoel Araújo was a Brazilian artist, curator, and cultural leader renowned for his work in promoting Afro-Brazilian art and heritage.
-
E.
Thiago Teixeira
Thiago Teixeira is a technology entrepreneur best known as a co-founder of the data app development platform Streamlit.
- 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_69d806aee7308190b70a237ba2a6e3e1 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98c9f0f148190a0698ef27573c885 |
completed | April 10, 2026, 11:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6f6136270819093256a143d2c9e65 |
completed | May 3, 2026, 7:15 a.m. |
| NEDg | Description generation | batch_69f6f72f9dcc8190aa07315891b393aa |
completed | May 3, 2026, 7:20 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69f6f812ae048190907b8def6b0d019c |
completed | May 3, 2026, 7:24 a.m. |
Created at: April 9, 2026, 9:17 p.m.