Triple
T18985920
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Target 5.b |
E464557
|
entity |
| Predicate | hasOfficialSource |
P83832
|
FINISHED |
| Object | United Nations SDG framework documents |
—
|
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: United Nations SDG framework documents | Statement: [Target 5.b, hasOfficialSource, United Nations SDG framework documents]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOfficialSource Context triple: [Target 5.b, hasOfficialSource, United Nations SDG framework documents]
-
A.
isOfficialSourceFor
chosen
Indicates that one entity is recognized as an authoritative or formally sanctioned provider of information or content about another entity.
-
B.
hasOfficial
Indicates that an entity is formally associated with, represented by, or served by a designated official or office-holder.
-
C.
hasOfficialSourceMonument
Indicates that something is recognized or documented as an official monument by an authoritative source or registry.
-
D.
isOfficial
Indicates that an entity holds formal, authorized, or government-recognized status in a given context.
-
E.
hasOfficialExplanation
Indicates that an entity is accompanied by an authoritative or formally recognized explanation clarifying its reason, cause, or details.
- 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_69d8dd008af48190a97ff1c6488edf1b |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d65f7f08819088f56e8e030851b1 |
completed | April 20, 2026, 7:31 a.m. |
| PD | Predicate disambiguation | batch_69e4a2f88e0c81908cb20f08bf24cd32 |
completed | April 19, 2026, 9:40 a.m. |
Created at: April 10, 2026, 12:01 p.m.