Triple
T14294976
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GATT 1994 Article XXI |
E354414
|
entity |
| Predicate | containsParagraph |
P33046
|
FINISHED |
| Object | Article XXI(a) |
—
|
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: Article XXI(a) | Statement: [GATT 1994 Article XXI, containsParagraph, Article XXI(a)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: containsParagraph Context triple: [GATT 1994 Article XXI, containsParagraph, Article XXI(a)]
-
A.
hasParagraph
chosen
Indicates that one entity contains or is associated with a specific paragraph as part of its content or structure.
-
B.
hasNumberOfParagraphs
Indicates that an entity is associated with a specific count of paragraphs it contains or comprises.
-
C.
hasTwoParagraphs
Indicates that the related content or text is composed of exactly two distinct paragraphs.
-
D.
containsText
Indicates that one entity includes the specified text string within its content.
-
E.
hasText
Indicates that an entity is associated with or contains a specific piece of textual content.
- 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_69d8278e17088190b328c5a9d4be74ff |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de717b35ec81908968994e65737c66 |
completed | April 14, 2026, 4:55 p.m. |
| PD | Predicate disambiguation | batch_69de2a8f81f08190af737e1654847aa6 |
completed | April 14, 2026, 11:52 a.m. |
Created at: April 10, 2026, 1:11 a.m.