Triple
T32517838
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Geneva Plan of Action |
E831104
|
entity |
| Predicate | targetRelatesTo |
P37
|
FINISHED |
| Object | Millennium Development Goals |
—
|
NE NERFINISHED |
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: Millennium Development Goals | Statement: [Geneva Plan of Action, targetRelatesTo, Millennium Development Goals]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: targetRelatesTo Context triple: [Geneva Plan of Action, targetRelatesTo, Millennium Development Goals]
-
A.
relatedTo
chosen
Indicates a general, non-specific relationship or association exists between two entities.
-
B.
termRelationTo
Indicates a general relational association between one term and another, without specifying the exact nature of that relationship.
-
C.
subjectRelation
Indicates that one entity stands in a specified relational role or connection to another entity.
-
D.
laterRelationWith
Indicates that one entity stands in a temporal relationship to another such that it occurs or exists at a later time than the other.
-
E.
trackRelationship
Indicates a connection in which one entity monitors, follows, or keeps a record of another entity’s state, behavior, or changes over time.
- 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_69f3492318348190ba37fb6b5f1d67f4 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fdf5d05cc481909ec9e1b1f0784279 |
completed | May 8, 2026, 2:40 p.m. |
| PD | Predicate disambiguation | batch_69fdf0cdd6948190838864ab3120dfa6 |
completed | May 8, 2026, 2:18 p.m. |
Created at: May 1, 2026, 1 a.m.