Triple
T12420696
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Steenokkerzeel |
E296760
|
entity |
| Predicate | hasSubdivision |
P747
|
FINISHED |
| Object |
Perk
Perk is a village in the Flemish Brabant province of Belgium, known as a rural sub-municipality of Steenokkerzeel.
|
E980425
|
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: Perk | Statement: [Steenokkerzeel, hasSubdivision, Perk]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Perk Context triple: [Steenokkerzeel, hasSubdivision, Perk]
-
A.
Perks Rewards
Perks Rewards is a membership tier offered by BJ's Wholesale Club that provides members with enhanced benefits and savings on their purchases.
-
B.
Power-Ups
Power-Ups are Trello add-ons that extend a board’s core functionality with integrations, custom views, and advanced features.
-
C.
Perka
Perka is a small settlement located on Car Nicobar Island in the Nicobar district of India’s Andaman and Nicobar Islands.
-
D.
Permet
Permet is a small town in southern Albania known for its scenic location along the Vjosa River, thermal springs, and surrounding mountainous landscapes.
-
E.
Augments
Augments are genetically enhanced humans in the Star Trek universe, engineered for superior physical and mental abilities but often associated with ambition and conflict.
- 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: Perk Triple: [Steenokkerzeel, hasSubdivision, Perk]
Generated description
Perk is a village in the Flemish Brabant province of Belgium, known as a rural sub-municipality of Steenokkerzeel.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Perk Target entity description: Perk is a village in the Flemish Brabant province of Belgium, known as a rural sub-municipality of Steenokkerzeel.
-
A.
Perks Rewards
Perks Rewards is a membership tier offered by BJ's Wholesale Club that provides members with enhanced benefits and savings on their purchases.
-
B.
Power-Ups
Power-Ups are Trello add-ons that extend a board’s core functionality with integrations, custom views, and advanced features.
-
C.
Perka
Perka is a small settlement located on Car Nicobar Island in the Nicobar district of India’s Andaman and Nicobar Islands.
-
D.
Permet
Permet is a small town in southern Albania known for its scenic location along the Vjosa River, thermal springs, and surrounding mountainous landscapes.
-
E.
Augments
Augments are genetically enhanced humans in the Star Trek universe, engineered for superior physical and mental abilities but often associated with ambition and conflict.
- 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_69d6ada0640c81908c061d7fb3d47786 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94d6efd748190a5d9396a343e41e1 |
completed | April 10, 2026, 7:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f634933b9881909fd592ede7c3e49c |
completed | May 2, 2026, 5:29 p.m. |
| NEDg | Description generation | batch_69f6356c21908190b34d1324da8f8052 |
completed | May 2, 2026, 5:33 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f63693f5c881909a9683a0c6a68739 |
completed | May 2, 2026, 5:38 p.m. |
Created at: April 8, 2026, 9:55 p.m.