Triple
T8225330
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sustainable Development Goal 3 |
E192160
|
entity |
| Predicate | hasIndicatorCount |
P9100
|
FINISHED |
| Object | 28 |
—
|
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: 28 | Statement: [Sustainable Development Goal 3, hasIndicatorCount, 28]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasIndicatorCount Context triple: [Sustainable Development Goal 3, hasIndicatorCount, 28]
-
A.
hasIndicatorDimension
Indicates that an indicator is associated with a specific dimension or aspect along which it is measured or evaluated.
-
B.
numberOfIndicators
chosen
Indicates the total count of indicators associated with or relevant to a given entity or context.
-
C.
hasVisualIndicator
Indicates that an entity is associated with some form of visual cue or marker that signals its status, condition, or presence.
-
D.
hasIndication
Indicates that one entity (typically a product, treatment, or intervention) is intended, approved, or suitable for use in addressing, preventing, or managing a particular condition, purpose, or circumstance.
-
E.
hasIndicationPopulation
Indicates that a medical indication is specifically applicable to, or defined for, a particular population group.
- 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_69ca82c9a8ac81908b011c38698456e4 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb77cdcc248190bc6c5b0271da8a08 |
completed | March 31, 2026, 7:29 a.m. |
| PD | Predicate disambiguation | batch_69cb36af41e081909dee92b9bc4947f1 |
completed | March 31, 2026, 2:51 a.m. |
Created at: March 30, 2026, 5:45 p.m.