Triple
T20689095
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Belgian railway line 57 |
E508500
|
entity |
| Predicate | connects |
P390
|
FINISHED |
| Object |
Sint-Margriete
Sint-Margriete is a village in the municipality of Sint-Laureins in East Flanders, Belgium, near the Dutch border.
|
E1445821
|
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: Sint-Margriete | Statement: [Belgian railway line 57, connects, Sint-Margriete]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sint-Margriete Context triple: [Belgian railway line 57, connects, Sint-Margriete]
-
A.
Sint-Joris
Sint-Joris is a village and sub-municipality of Nieuwpoort in West Flanders, Belgium, known for its rural character and proximity to the Yser River.
-
B.
Hoog Catharijne
Hoog Catharijne is a large, modern shopping mall and transit hub in the center of Utrecht, Netherlands.
-
C.
Margriete de Vos
Margriete de Vos was a Flemish woman best known as the wife of prominent Baroque painter and animal still-life specialist Frans Snyders.
-
D.
Saint Gudula
Saint Gudula is a 7th–8th century Belgian saint venerated as the patroness of Brussels, often depicted with a lantern symbolizing her piety and miracles.
-
E.
Geertruida
Geertruida is a Dutch feminine given name, corresponding to the English name Gertrude.
- 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: Sint-Margriete Triple: [Belgian railway line 57, connects, Sint-Margriete]
Generated description
Sint-Margriete is a village in the municipality of Sint-Laureins in East Flanders, Belgium, near the Dutch border.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sint-Margriete Target entity description: Sint-Margriete is a village in the municipality of Sint-Laureins in East Flanders, Belgium, near the Dutch border.
-
A.
Sint-Joris
Sint-Joris is a village and sub-municipality of Nieuwpoort in West Flanders, Belgium, known for its rural character and proximity to the Yser River.
-
B.
Hoog Catharijne
Hoog Catharijne is a large, modern shopping mall and transit hub in the center of Utrecht, Netherlands.
-
C.
Margriete de Vos
Margriete de Vos was a Flemish woman best known as the wife of prominent Baroque painter and animal still-life specialist Frans Snyders.
-
D.
Saint Gudula
Saint Gudula is a 7th–8th century Belgian saint venerated as the patroness of Brussels, often depicted with a lantern symbolizing her piety and miracles.
-
E.
Geertruida
Geertruida is a Dutch feminine given name, corresponding to the English name Gertrude.
- 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_69e0b4c1ed408190b72dd26b1e33f8a1 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6c10b7b808190bdb8b08e53168fb8 |
completed | April 21, 2026, 12:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a08d7e226808190bf05b85afb173e36 |
completed | May 16, 2026, 8:47 p.m. |
| NEDg | Description generation | batch_6a08d9ca43288190a2be3d4f63141391 |
completed | May 16, 2026, 8:55 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a08da457ee48190ba18b3e34f117e19 |
completed | May 16, 2026, 8:57 p.m. |
Created at: April 16, 2026, 11:56 a.m.