Triple
T24841000
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Inga II Dam |
E621611
|
entity |
| Predicate | fundingSupportFrom |
P67
|
FINISHED |
| Object | World Bank |
—
|
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: World Bank | Statement: [Inga II Dam, fundingSupportFrom, World Bank]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fundingSupportFrom Context triple: [Inga II Dam, fundingSupportFrom, World Bank]
-
A.
fundedBy
chosen
Indicates that an entity receives financial support or resources from another entity.
-
B.
funderOf
Indicates that one entity provides financial support or funding for another entity, project, or activity.
-
C.
permittedFundingFrom
Indicates that providing financial resources from one entity to another is allowed under specified rules or conditions.
-
D.
foundedWithSupportFrom
Indicates that an entity was established or created with assistance, backing, or resources provided by another entity.
-
E.
seeksFundingFrom
Indicates that one entity is actively trying to obtain financial support or investment from another entity.
- 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_69e2fac185d48190a0a6073ad1f6b792 |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f43043512481909501a3979cac9947 |
completed | May 1, 2026, 4:46 a.m. |
| PD | Predicate disambiguation | batch_69f420fd375c81908ea4a4e60b76ee8f |
completed | May 1, 2026, 3:41 a.m. |
Created at: April 18, 2026, 5:18 a.m.