Triple
T4850377
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pfizer |
E108398
|
entity |
| Predicate | developed |
P73
|
FINISHED |
| Object | Viagra |
E291801
|
NE FINISHED |
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: Viagra | Statement: [Pfizer, developed, Viagra]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Viagra Context triple: [Pfizer, developed, Viagra]
-
A.
Viagra
chosen
Viagra is a well-known prescription medication used to treat erectile dysfunction by increasing blood flow to the penis.
-
B.
Propecia
Propecia is a brand-name prescription medication (finasteride) primarily used to treat male pattern hair loss.
-
C.
Pille
Pille is the talking football character that served as the sidekick to Goleo VI, the official mascot of the 2006 FIFA World Cup in Germany.
-
D.
Doxato
Doxato is a town in northern Greece located within the Drama regional unit, known for its agricultural surroundings and historical significance.
-
E.
Truvada
Truvada is a prescription antiretroviral medication widely used both to treat HIV infection and as pre-exposure prophylaxis (PrEP) to help prevent HIV in high-risk individuals.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69bd440a89548190a5f14ba6da6b97dc |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6d1e5cf08190bd6b6a524748f170 |
completed | March 20, 2026, 3:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be5cdefda8819095fbc04446bf32f5 |
completed | March 21, 2026, 8:54 a.m. |
Created at: March 20, 2026, 1:25 p.m.