Triple
T3379764
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | WTO panels |
E71152
|
entity |
| Predicate | mustFollow |
P134
|
FINISHED |
| Object | Dispute Settlement Understanding procedures |
—
|
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: Dispute Settlement Understanding procedures | Statement: [WTO panels, mustFollow, Dispute Settlement Understanding procedures]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mustFollow Context triple: [WTO panels, mustFollow, Dispute Settlement Understanding procedures]
-
A.
mustMeet
Indicates that one entity is required or obligated to have a meeting or encounter with another entity.
-
B.
mustRespect
Indicates that one entity is obligated to show respect or deference toward another entity.
-
C.
mustActIn
Indicates that an entity is required or obligated to perform an action within a specified context, domain, or timeframe.
-
D.
follows
chosen
Indicates that one entity comes after, moves behind, or acts in accordance with another entity in time, space, or sequence.
-
E.
mayBeFollowedBy
Indicates that one event, state, or item is allowed or able to occur immediately after another in a sequence.
- 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_69ad85a7f80c8190a05e43013f298942 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb2ec38d88190be8c824daeca5ab6 |
completed | March 8, 2026, 5:33 p.m. |
| PD | Predicate disambiguation | batch_69ada434bae48190a77ea37f9274ad8f |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:14 p.m.