Triple
T32733877
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Combined Nomenclature |
E837023
|
entity |
| Predicate | updateEffectiveDate |
P69126
|
FINISHED |
| Object | 1 January each year |
—
|
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: 1 January each year | Statement: [Combined Nomenclature, updateEffectiveDate, 1 January each year]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: updateEffectiveDate Context triple: [Combined Nomenclature, updateEffectiveDate, 1 January each year]
-
A.
extensionEffectiveDate
Indicates the date on which an extension to an existing agreement, term, or condition becomes effective.
-
B.
currentVersionEffectiveDate
chosen
Indicates the date from which the current version of an item, record, or agreement becomes valid and in effect.
-
C.
decisionEffectiveDate
Indicates the date on which a particular decision becomes valid, operative, or officially takes effect.
-
D.
administrativeChangeDate
Indicates the date on which an administrative change (such as an update, modification, or reclassification) affecting the entity was officially recorded or took effect.
-
E.
updatedSpecificationDate
Indicates the date on which a specification was last revised or brought up to date.
- 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_69f34935fb048190ad4967420581f835 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6cd126fcc8190aa1f1f146e45ec0c |
completed | May 3, 2026, 4:20 a.m. |
| PD | Predicate disambiguation | batch_69f6cc1470808190b70cdfd7a6395670 |
completed | May 3, 2026, 4:16 a.m. |
Created at: May 1, 2026, 1:11 a.m.