Triple
T33863111
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ILO Maritime Labour Convention |
E867972
|
entity |
| Predicate | codeDividedInto |
P99142
|
FINISHED |
| Object | Part A (mandatory standards) |
—
|
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: Part A (mandatory standards) | Statement: [ILO Maritime Labour Convention, codeDividedInto, Part A (mandatory standards)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: codeDividedInto Context triple: [ILO Maritime Labour Convention, codeDividedInto, Part A (mandatory standards)]
-
A.
dividedIn
chosen
Indicates that one entity is partitioned or separated into multiple distinct parts, sections, or groups represented by another entity.
-
B.
sometimesDividedInto
Indicates that an entity is on some occasions partitioned or separated into distinct parts, sections, or groups, but not always.
-
C.
codeSection
Indicates a specific segment or subsection within a larger body of code that is distinguished for reference, organization, or analysis.
-
D.
classDivision
Indicates a hierarchical separation or grouping of entities into distinct classes or tiers based on defined criteria.
-
E.
codeSeparator
Indicates a relationship where one element serves to divide or distinguish segments of code from each other.
- 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_69f349943ccc8190a3c41a3e0ae46cbf |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f700a00d048190b2af302cc0e982c4 |
completed | May 3, 2026, 8 a.m. |
| PD | Predicate disambiguation | batch_69f6fc5a4f7881909324eb3c20ca96f1 |
completed | May 3, 2026, 7:42 a.m. |
Created at: May 1, 2026, 1:47 a.m.