Triple
T5948078
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Douala |
E132327
|
entity |
| Predicate | hasFootballClub |
P346
|
FINISHED |
| Object |
AS Matelots de Douala
AS Matelots de Douala is a Cameroonian football club based in the city of Douala.
|
E557634
|
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: AS Matelots de Douala | Statement: [Douala, hasFootballClub, AS Matelots de Douala]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: AS Matelots de Douala Context triple: [Douala, hasFootballClub, AS Matelots de Douala]
-
A.
Taganga
Taganga is a small fishing village and popular backpacker destination on Colombia’s Caribbean coast, known for its beaches, diving, and proximity to Tayrona National Natural Park.
-
B.
Gourette
Gourette is a French mountain ski resort village in the Pyrenees, known for its alpine slopes and scenic high-altitude setting.
-
C.
Wagadou
Wagadou is the historical name for the Ghana Empire, a powerful West African trading state that flourished between the 6th and 13th centuries.
-
D.
Tous
Tous is a Spanish jewelry and accessories brand known for its distinctive teddy bear logo and affordable luxury designs.
-
E.
Ten-Go
Ten-Go was the codename for Japan’s final major naval operation in World War II, centered on the battleship Yamato’s doomed sortie toward Okinawa in April 1945.
- 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: AS Matelots de Douala Triple: [Douala, hasFootballClub, AS Matelots de Douala]
Generated description
AS Matelots de Douala is a Cameroonian football club based in the city of Douala.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: AS Matelots de Douala Target entity description: AS Matelots de Douala is a Cameroonian football club based in the city of Douala.
-
A.
Taganga
Taganga is a small fishing village and popular backpacker destination on Colombia’s Caribbean coast, known for its beaches, diving, and proximity to Tayrona National Natural Park.
-
B.
Gourette
Gourette is a French mountain ski resort village in the Pyrenees, known for its alpine slopes and scenic high-altitude setting.
-
C.
Wagadou
Wagadou is the historical name for the Ghana Empire, a powerful West African trading state that flourished between the 6th and 13th centuries.
-
D.
Tous
Tous is a Spanish jewelry and accessories brand known for its distinctive teddy bear logo and affordable luxury designs.
-
E.
Ten-Go
Ten-Go was the codename for Japan’s final major naval operation in World War II, centered on the battleship Yamato’s doomed sortie toward Okinawa in April 1945.
- 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_69c00869d3308190af89b2453e0f7546 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c0397c80708190a4778fdb353314b7 |
completed | March 22, 2026, 6:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c0c08d4f0481908547609bc2736380 |
completed | March 23, 2026, 4:24 a.m. |
| NEDg | Description generation | batch_69c0c19665b08190ab3c66b7c6c33f61 |
completed | March 23, 2026, 4:29 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c0c4576824819080ced71df8fdda6c |
completed | March 23, 2026, 4:40 a.m. |
Created at: March 22, 2026, 4:01 p.m.