Triple
T18644832
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Novo Nordisk |
E455777
|
entity |
| Predicate | formedByMergerOf |
P77
|
FINISHED |
| Object |
Novo Industri
Novo Industri was a Danish pharmaceutical and biotechnology company that became part of Novo Nordisk through a corporate merger.
|
E1335206
|
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: Novo Industri | Statement: [Novo Nordisk, formedByMergerOf, Novo Industri]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Novo Industri Context triple: [Novo Nordisk, formedByMergerOf, Novo Industri]
-
A.
Shao Industries
Shao Industries is a company or corporate entity associated with and employing Liwen Shao.
-
B.
ANF Industrie
ANF Industrie is a French rolling stock manufacturer known for producing railway and metro vehicles, including subway cars such as the R68 for the New York City Subway.
-
C.
Vinnova
Vinnova is Sweden’s government agency for innovation, supporting research, entrepreneurship, and sustainable growth through funding and strategic initiatives.
-
D.
Confimi Industria
Confimi Industria is an Italian employers' association representing industrial and manufacturing companies within the national confederation system.
-
E.
Nissho
Nissho was a prominent disciple of the Japanese Buddhist monk Nichiren who helped propagate and systematize Nichiren Buddhism.
- 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: Novo Industri Triple: [Novo Nordisk, formedByMergerOf, Novo Industri]
Generated description
Novo Industri was a Danish pharmaceutical and biotechnology company that became part of Novo Nordisk through a corporate merger.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Novo Industri Target entity description: Novo Industri was a Danish pharmaceutical and biotechnology company that became part of Novo Nordisk through a corporate merger.
-
A.
Shao Industries
Shao Industries is a company or corporate entity associated with and employing Liwen Shao.
-
B.
ANF Industrie
ANF Industrie is a French rolling stock manufacturer known for producing railway and metro vehicles, including subway cars such as the R68 for the New York City Subway.
-
C.
Vinnova
Vinnova is Sweden’s government agency for innovation, supporting research, entrepreneurship, and sustainable growth through funding and strategic initiatives.
-
D.
Confimi Industria
Confimi Industria is an Italian employers' association representing industrial and manufacturing companies within the national confederation system.
-
E.
Nissho
Nissho was a prominent disciple of the Japanese Buddhist monk Nichiren who helped propagate and systematize Nichiren Buddhism.
- 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_69d8d38ea1e88190997e9b231190ba6f |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5500c36188190bfdd7aca73f3c006 |
completed | April 19, 2026, 9:58 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a050d865fc48190a11ed96ebfdca50d |
completed | May 13, 2026, 11:47 p.m. |
| NEDg | Description generation | batch_6a051058f5788190b782a39feb7f6111 |
completed | May 13, 2026, 11:59 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0510fc0d1081908970c91357bb3444 |
completed | May 14, 2026, 12:02 a.m. |
Created at: April 10, 2026, 11:47 a.m.