Triple
T1717088
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | War on Drugs |
E37313
|
entity |
| Predicate | focusSubstance |
P31
|
FINISHED |
| Object | cocaine |
—
|
LITERAL 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: cocaine | Statement: [War on Drugs, focusSubstance, cocaine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: focusSubstance Context triple: [War on Drugs, focusSubstance, cocaine]
-
A.
substanceType
Indicates the specific kind or category of substance associated with an entity or relation.
-
B.
focusesOn
chosen
Indicates that one entity directs its attention, effort, or primary activity toward another entity or specific subject.
-
C.
subjectMatter
Indicates the topic, theme, or content area that something (such as a work, document, or discussion) is about.
-
D.
formulatedIn
Indicates that something was created, developed, or expressed within a particular context, place, or framework.
-
E.
chemicallyRelatedTo
Indicates a relationship where two entities are connected through a chemical association, such as sharing structural features, participating in related reactions, or being derivable from one another chemically.
- F. None of above.
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_69a8861912dc8190931af43b4b9158a7 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69ab5c96db6c8190a745d6fef7bf2cdb |
completed | March 6, 2026, 11 p.m. |
| PD | Predicate disambiguation | batch_69aa61bed2fc819086d912cd34285978 |
completed | March 6, 2026, 5:10 a.m. |
Created at: March 4, 2026, 7:30 p.m.