Triple
T4952236
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Great Green Wall |
E111193
|
entity |
| Predicate | hasPlannedLength |
P22512
|
FINISHED |
| Object | approximately 8000 kilometers |
—
|
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: approximately 8000 kilometers | Statement: [Great Green Wall, hasPlannedLength, approximately 8000 kilometers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPlannedLength Context triple: [Great Green Wall, hasPlannedLength, approximately 8000 kilometers]
-
A.
plannedExtensionLength
chosen
Indicates the intended or proposed length of an extension as specified in a plan or design.
-
B.
hasPlanningStatus
Indicates that an entity is associated with a particular stage, condition, or outcome in a planning or approval process.
-
C.
hasPlanningLevel
Indicates that an entity is associated with a specific stage, tier, or granularity within a planning or scheduling hierarchy.
-
D.
plannedHeight
Indicates the intended or designed vertical size or elevation that something is planned to have.
-
E.
numberPlanned
Indicates that a specific quantity has been scheduled or intended for a future action or allocation.
- 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_69bd4418390c8190b7e9766a2512ce55 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd71b6a5d481909ad6f5e0b752496c |
completed | March 20, 2026, 4:11 p.m. |
| PD | Predicate disambiguation | batch_69bd6c3aa1388190b3e0c8ee1ba1e4fa |
completed | March 20, 2026, 3:48 p.m. |
Created at: March 20, 2026, 1:31 p.m.