Triple
T22694320
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fiskars Corporation |
E561130
|
entity |
| Predicate | hasDivision |
P35
|
FINISHED |
| Object |
Crea
Crea is a division of Fiskars Corporation focused on creative and crafting products and solutions.
|
E1551075
|
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: Crea | Statement: [Fiskars Corporation, hasDivision, Crea]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Crea Context triple: [Fiskars Corporation, hasDivision, Crea]
-
A.
CREA
CREA is a large reference corpus of contemporary Spanish used for linguistic research and language analysis.
-
B.
CREI
CREI is a Barcelona-based research institute specializing in macroeconomics and international economics, closely linked to academic institutions such as Universitat Pompeu Fabra.
-
C.
Bigweld
Bigweld is a charismatic, visionary inventor and industrialist from the animated film "Robots," known for championing creativity and innovation in a robot-populated world.
-
D.
Maquinna
Maquinna was a prominent 18th–19th century Nuu-chah-nulth chief known for his influential role in early contacts and trade with European explorers on the Pacific Northwest Coast.
-
E.
Ellmaker
Ellmaker is a surname most notably associated with Amos Ellmaker, a 19th-century American politician and lawyer.
- 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: Crea Triple: [Fiskars Corporation, hasDivision, Crea]
Generated description
Crea is a division of Fiskars Corporation focused on creative and crafting products and solutions.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Crea Target entity description: Crea is a division of Fiskars Corporation focused on creative and crafting products and solutions.
-
A.
CREA
CREA is a large reference corpus of contemporary Spanish used for linguistic research and language analysis.
-
B.
CREI
CREI is a Barcelona-based research institute specializing in macroeconomics and international economics, closely linked to academic institutions such as Universitat Pompeu Fabra.
-
C.
Bigweld
Bigweld is a charismatic, visionary inventor and industrialist from the animated film "Robots," known for championing creativity and innovation in a robot-populated world.
-
D.
Maquinna
Maquinna was a prominent 18th–19th century Nuu-chah-nulth chief known for his influential role in early contacts and trade with European explorers on the Pacific Northwest Coast.
-
E.
Ellmaker
Ellmaker is a surname most notably associated with Amos Ellmaker, a 19th-century American politician and lawyer.
- 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_69e2454e615481909c177440be559d2c |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1789d46c881908176bc8e26f366f6 |
completed | April 29, 2026, 3:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0b7ece75648190a841256cf08a72f8 |
completed | May 18, 2026, 9:04 p.m. |
| NEDg | Description generation | batch_6a0b834f488c8190bee40bd1caea0e40 |
completed | May 18, 2026, 9:23 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0b8717b65c819089d29c1802d1ed55 |
completed | May 18, 2026, 9:39 p.m. |
Created at: April 17, 2026, 3:14 p.m.