Triple
T9296973
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harmonized System Committee |
E223661
|
entity |
| Predicate | usesCodeStructure |
P66347
|
FINISHED |
| Object | 6-digit Harmonized System codes |
—
|
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: 6-digit Harmonized System codes | Statement: [Harmonized System Committee, usesCodeStructure, 6-digit Harmonized System codes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesCodeStructure Context triple: [Harmonized System Committee, usesCodeStructure, 6-digit Harmonized System codes]
-
A.
programStructure
Indicates how components, modules, or elements are organized and related within a program or system.
-
B.
usesCodeSpace
chosen
Indicates that one entity employs or operates within a particular code space or coding environment provided by another entity.
-
C.
usedStructure
Indicates that one entity makes use of, relies on, or operates through a particular structure (physical, logical, or organizational) to perform its function or action.
-
D.
codeFor
Indicates that one entity serves as the implementation, encoding, or programmatic representation for another entity.
-
E.
hasCodeIn
Indicates that one entity is represented, defined, or implemented within the codebase or coding context of another entity.
- 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_69ca8423edb08190bc0c91287a484768 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd089c9c588190967404c9eb938dfb |
completed | April 1, 2026, 11:59 a.m. |
| PD | Predicate disambiguation | batch_69cc7a5aeb748190afb89c6bbd2a6d6f |
completed | April 1, 2026, 1:52 a.m. |
Created at: March 30, 2026, 7:36 p.m.