Triple
T6006184
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sanofi |
E133715
|
entity |
| Predicate | subsidiary |
P258
|
FINISHED |
| Object |
Genzyme
Genzyme is a biotechnology company best known for developing treatments for rare genetic disorders and other specialty diseases.
|
E561775
|
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: Genzyme | Statement: [Sanofi, subsidiary, Genzyme]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Genzyme Context triple: [Sanofi, subsidiary, Genzyme]
-
A.
Alexion Pharmaceuticals
Alexion Pharmaceuticals is a biopharmaceutical company specializing in the development of therapies for rare and severe diseases, particularly in the field of complement biology.
-
B.
Biogen
Biogen is a major American biotechnology company known for developing therapies for neurological and neurodegenerative diseases.
-
C.
Genmab
Genmab is a Danish biotechnology company specializing in the development of antibody-based cancer therapies.
-
D.
Novartis
Novartis is a global Swiss-based pharmaceutical company known for developing innovative medicines across a wide range of therapeutic areas.
-
E.
Novo Nordisk
Novo Nordisk is a global healthcare company based in Denmark, best known as a leading producer of insulin and other diabetes care treatments.
- 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: Genzyme Triple: [Sanofi, subsidiary, Genzyme]
Generated description
Genzyme is a biotechnology company best known for developing treatments for rare genetic disorders and other specialty diseases.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Genzyme Target entity description: Genzyme is a biotechnology company best known for developing treatments for rare genetic disorders and other specialty diseases.
-
A.
Alexion Pharmaceuticals
Alexion Pharmaceuticals is a biopharmaceutical company specializing in the development of therapies for rare and severe diseases, particularly in the field of complement biology.
-
B.
Biogen
Biogen is a major American biotechnology company known for developing therapies for neurological and neurodegenerative diseases.
-
C.
Bristol Myers Squibb
Bristol Myers Squibb is a global biopharmaceutical company known for developing and manufacturing innovative medicines in areas such as oncology, immunology, and cardiovascular disease.
-
D.
Genmab
Genmab is a Danish biotechnology company specializing in the development of antibody-based cancer therapies.
-
E.
Novartis
Novartis is a global Swiss-based pharmaceutical company known for developing innovative medicines across a wide range of therapeutic areas.
- 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_69c00872444c8190bfaf1739dcec765c |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c04f128354819088971ee398cbda77 |
completed | March 22, 2026, 8:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c10895559081908b9efdd32ecef37f |
completed | March 23, 2026, 9:32 a.m. |
| NEDg | Description generation | batch_69c10b7467e88190955014bc060b20e4 |
completed | March 23, 2026, 9:44 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c10c0a001c81908e3ca53e9491ff9a |
completed | March 23, 2026, 9:46 a.m. |
Created at: March 22, 2026, 4:06 p.m.