Triple
T12151662
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Culemborg |
E289469
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object |
Binnenpoort
Binnenpoort is a historic city gate in Culemborg in the Netherlands, notable as a remnant of the town’s medieval fortifications.
|
E970174
|
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: Binnenpoort | Statement: [Culemborg, hasLandmark, Binnenpoort]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Binnenpoort Context triple: [Culemborg, hasLandmark, Binnenpoort]
-
A.
Gevangenpoort
Gevangenpoort is a historic city gate and former prison in Bergen op Zoom, Netherlands, known as one of the town’s most prominent medieval landmarks.
-
B.
Blokhuispoort
Blokhuispoort is a former prison complex in Leeuwarden, Netherlands, that has been transformed into a cultural and creative hub with museums, studios, and public spaces.
-
C.
Broederpoort
Broederpoort is a historic city gate in Kampen, the Netherlands, known for its well-preserved Renaissance architecture.
-
D.
De Waterkant
De Waterkant is a trendy, historic neighborhood in Cape Town known for its cobbled streets, colorful cottages, and vibrant café and nightlife scene.
-
E.
De Koperwiek
De Koperwiek is a major shopping center in Capelle aan den IJssel, Netherlands, featuring a variety of retail stores, services, and dining options.
- 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: Binnenpoort Triple: [Culemborg, hasLandmark, Binnenpoort]
Generated description
Binnenpoort is a historic city gate in Culemborg in the Netherlands, notable as a remnant of the town’s medieval fortifications.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Binnenpoort Target entity description: Binnenpoort is a historic city gate in Culemborg in the Netherlands, notable as a remnant of the town’s medieval fortifications.
-
A.
Gevangenpoort
Gevangenpoort is a historic city gate and former prison in Bergen op Zoom, Netherlands, known as one of the town’s most prominent medieval landmarks.
-
B.
Blokhuispoort
Blokhuispoort is a former prison complex in Leeuwarden, Netherlands, that has been transformed into a cultural and creative hub with museums, studios, and public spaces.
-
C.
Broederpoort
Broederpoort is a historic city gate in Kampen, the Netherlands, known for its well-preserved Renaissance architecture.
-
D.
De Waterkant
De Waterkant is a trendy, historic neighborhood in Cape Town known for its cobbled streets, colorful cottages, and vibrant café and nightlife scene.
-
E.
De Koperwiek
De Koperwiek is a major shopping center in Capelle aan den IJssel, Netherlands, featuring a variety of retail stores, services, and dining options.
- 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_69d6ab4c6710819097a9d228382dde43 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d915ae736c8190aaab05efb93c5854 |
completed | April 10, 2026, 3:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f60a80aa6881908111cc47b5fe8b9e |
completed | May 2, 2026, 2:30 p.m. |
| NEDg | Description generation | batch_69f60c9276d0819086b5f7712fe8d6e6 |
completed | May 2, 2026, 2:39 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f60d4889d48190b2dfda8a0978cc72 |
completed | May 2, 2026, 2:42 p.m. |
Created at: April 8, 2026, 9:49 p.m.