Triple
T13739580
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Geraardsbergen |
E330048
|
entity |
| Predicate | knownFor |
P22
|
FINISHED |
| Object |
mattentaart
Mattentaart is a traditional Belgian pastry from Geraardsbergen, made with a rich filling of curd cheese and almonds in a flaky puff pastry crust.
|
E1057661
|
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: mattentaart | Statement: [Geraardsbergen, knownFor, mattentaart]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: mattentaart Context triple: [Geraardsbergen, knownFor, mattentaart]
-
A.
Mattokki
Mattokki is an alternative name used by the artist or creator known as Kenzi.
-
B.
Mattokki
Mattokki is a lesser-known Nubian language spoken by a small ethnic community in the Nile Valley region of northeastern Africa.
-
C.
MANTAK
MANTAK is the Israeli defense organization responsible for developing and overseeing the Merkava main battle tank program.
-
D.
Matanvat
Matanvat is a village where the Nese language is traditionally spoken.
-
E.
Vansittart
Vansittart is a British surname historically associated with politicians, civil servants, and other notable public figures.
- 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: mattentaart Triple: [Geraardsbergen, knownFor, mattentaart]
Generated description
Mattentaart is a traditional Belgian pastry from Geraardsbergen, made with a rich filling of curd cheese and almonds in a flaky puff pastry crust.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: mattentaart Target entity description: Mattentaart is a traditional Belgian pastry from Geraardsbergen, made with a rich filling of curd cheese and almonds in a flaky puff pastry crust.
-
A.
Mattokki
Mattokki is a lesser-known Nubian language spoken by a small ethnic community in the Nile Valley region of northeastern Africa.
-
B.
Mattokki
Mattokki is an alternative name used by the artist or creator known as Kenzi.
-
C.
MANTAK
MANTAK is the Israeli defense organization responsible for developing and overseeing the Merkava main battle tank program.
-
D.
Matanvat
Matanvat is a village where the Nese language is traditionally spoken.
-
E.
Vansittart
Vansittart is a British surname historically associated with politicians, civil servants, and other notable public figures.
- 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_69d80772315881908f980cae40d91664 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69de0204d50c8190a5413cc9a1b26e14 |
completed | April 14, 2026, 8:59 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f79d6bce9881909209231f6dfcf9bf |
completed | May 3, 2026, 7:09 p.m. |
| NEDg | Description generation | batch_69f79e7869648190ab0157bd0480b219 |
completed | May 3, 2026, 7:14 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f79f7216b08190800165d46172222c |
completed | May 3, 2026, 7:18 p.m. |
Created at: April 9, 2026, 9:55 p.m.