Triple
T22339828
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amsterdam harbor system |
E552243
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object |
Afrikahaven
Afrikahaven is a major industrial and logistics port area within Amsterdam’s harbor complex, primarily serving bulk cargo and maritime trade operations.
|
E1530790
|
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: Afrikahaven | Statement: [Amsterdam harbor system, hasPart, Afrikahaven]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Afrikahaven Context triple: [Amsterdam harbor system, hasPart, Afrikahaven]
-
A.
Binnenhaven
Binnenhaven is a harbor area in the city of Hasselt, Belgium, used primarily for inland shipping and local waterfront activities.
-
B.
Haveneiland
Haveneiland is a residential artificial island in Amsterdam’s IJburg district, known for its modern urban planning and waterfront living.
-
C.
Baheri
Baheri is a town located in the Darbhanga district of the Indian state of Bihar.
-
D.
Outremer
Outremer was the collective name for the Crusader states established by Western European Christians in the Levant during the Middle Ages.
-
E.
Baie des Fourmis
Baie des Fourmis is a small, picturesque Mediterranean beach on the French Riviera, located in the coastal town of Beaulieu-sur-Mer near Nice.
- 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: Afrikahaven Triple: [Amsterdam harbor system, hasPart, Afrikahaven]
Generated description
Afrikahaven is a major industrial and logistics port area within Amsterdam’s harbor complex, primarily serving bulk cargo and maritime trade operations.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Afrikahaven Target entity description: Afrikahaven is a major industrial and logistics port area within Amsterdam’s harbor complex, primarily serving bulk cargo and maritime trade operations.
-
A.
Binnenhaven
Binnenhaven is a harbor area in the city of Hasselt, Belgium, used primarily for inland shipping and local waterfront activities.
-
B.
Haveneiland
Haveneiland is a residential artificial island in Amsterdam’s IJburg district, known for its modern urban planning and waterfront living.
-
C.
Baheri
Baheri is a town located in the Darbhanga district of the Indian state of Bihar.
-
D.
Outremer
Outremer was the collective name for the Crusader states established by Western European Christians in the Levant during the Middle Ages.
-
E.
Baie des Fourmis
Baie des Fourmis is a small, picturesque Mediterranean beach on the French Riviera, located in the coastal town of Beaulieu-sur-Mer near Nice.
- 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_69e11e494eec81909c4d2d51f69499d9 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f157824f588190882bea9e61dd5a83 |
completed | April 29, 2026, 12:57 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0ad52d8b488190b9cba9b47f8f6e3d |
completed | May 18, 2026, 9 a.m. |
| NEDg | Description generation | batch_6a0ad993b9188190aacf482038b3cd29 |
completed | May 18, 2026, 9:19 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0ada0cef848190864a88d7baa24a81 |
completed | May 18, 2026, 9:21 a.m. |
Created at: April 16, 2026, 8:43 p.m.