Triple
T19773558
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Allergan |
E474948
|
entity |
| Predicate | mergedWith |
P77
|
FINISHED |
| Object | Actavis |
—
|
NE NERFINISHED |
How this triple was built (2 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: Actavis | Statement: [Allergan, mergedWith, Actavis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Actavis Context triple: [Allergan, mergedWith, Actavis]
-
A.
Actavis plc
chosen
Actavis plc was a global specialty pharmaceutical company known for its extensive portfolio of generic and branded drugs before rebranding as Allergan.
-
B.
Mylan
Mylan is a global generic and specialty pharmaceuticals company known for producing a wide range of affordable medicines and healthcare products.
-
C.
Cephalon
Cephalon was a biopharmaceutical company known for developing and marketing specialty drugs in areas such as central nervous system disorders, pain management, and oncology.
-
D.
Optax
Optax is a gradient processing and optimization library for JAX, providing a flexible collection of composable optimizers and transformations for training machine learning models.
-
E.
Sandoz
Sandoz is a historic Swiss pharmaceutical company best known as a predecessor of Novartis and a major player in generic medicines.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e51a43a08190956bc6df13c91a77 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6535e450c8190a2628245ae0d0bd3 |
completed | April 20, 2026, 4:25 p.m. |
Created at: April 10, 2026, 1:48 p.m.