Triple
T9851931
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rromani |
E239489
|
entity |
| Predicate | hasSubgroup |
P747
|
FINISHED |
| Object |
Finnish Kale
Finnish Kale are a Romani subgroup in Finland with a distinct culture, history, and dialect shaped by centuries of life in the Nordic region.
|
E824965
|
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: Finnish Kale | Statement: [Rromani, hasSubgroup, Finnish Kale]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Finnish Kale Context triple: [Rromani, hasSubgroup, Finnish Kale]
-
A.
Kale
Kale is a small irregular moon of Jupiter belonging to the planet’s distant, retrograde outer satellite group.
-
B.
Kale
Kale is a town in Myanmar’s Sagaing Region, known as a local commercial and transport hub in the country’s northwest.
-
C.
Chard
Chard is a historic market town in Somerset, England, often noted for its claim as the birthplace of powered flight and as one of the county’s southernmost towns.
-
D.
Leek
Leek is a historic market town in Staffordshire, England, known for its textile heritage and picturesque location near the Peak District.
-
E.
Leek
Leek is a former municipality in the Dutch province of Groningen, known for its rural character and historic estates, that was incorporated into the municipality of Westerkwartier.
- 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: Finnish Kale Triple: [Rromani, hasSubgroup, Finnish Kale]
Generated description
Finnish Kale are a Romani subgroup in Finland with a distinct culture, history, and dialect shaped by centuries of life in the Nordic region.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Finnish Kale Target entity description: Finnish Kale are a Romani subgroup in Finland with a distinct culture, history, and dialect shaped by centuries of life in the Nordic region.
-
A.
Kale
Kale is a small irregular moon of Jupiter belonging to the planet’s distant, retrograde outer satellite group.
-
B.
Kale
Kale is a town in Myanmar’s Sagaing Region, known as a local commercial and transport hub in the country’s northwest.
-
C.
Chard
Chard is a historic market town in Somerset, England, often noted for its claim as the birthplace of powered flight and as one of the county’s southernmost towns.
-
D.
Leek
Leek is a historic market town in Staffordshire, England, known for its textile heritage and picturesque location near the Peak District.
-
E.
Leek
Leek is a former municipality in the Dutch province of Groningen, known for its rural character and historic estates, that was incorporated into the municipality of Westerkwartier.
- 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_69ca84e4fdc08190a624425bcef98665 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb375ba448190a32cca2b0f376ac1 |
completed | April 2, 2026, 12:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1d5ee190c8190957451d8d8291df3 |
completed | April 5, 2026, 3:24 a.m. |
| NEDg | Description generation | batch_69d1d6a385ac8190b5dd11adfbb7578d |
completed | April 5, 2026, 3:27 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d1d75210f4819096ee05a8b870581e |
completed | April 5, 2026, 3:30 a.m. |
Created at: March 30, 2026, 8:34 p.m.