Triple
T12168054
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Greater Lebanon |
E289884
|
entity |
| Predicate | formedBasisFor |
P34379
|
FINISHED |
| Object | modern state of Lebanon |
—
|
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: modern state of Lebanon | Statement: [Greater Lebanon, formedBasisFor, modern state of Lebanon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formedBasisFor Context triple: [Greater Lebanon, formedBasisFor, modern state of Lebanon]
-
A.
hasBasisIn
Indicates that one entity is founded, derived, or justified on the grounds of another entity.
-
B.
proposedRepresentationBasis
Indicates that one entity has been put forward as the foundational or reference basis for representing or encoding another entity.
-
C.
becameBasisOf
chosen
Indicates that one entity served as the foundational source, model, or starting point upon which another entity was developed, derived, or established.
-
D.
formedBy
Indicates that something comes into existence or is created as a result of a specific agent, process, or combination of components.
-
E.
hasCanonicalBasis
Indicates that there exists a standard or preferred basis associated with an entity, typically used as the reference basis in its context.
- 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_69d6ab4d6c00819095a9a7c35de83cfb |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d91621ca6c81908365732f361aef13 |
completed | April 10, 2026, 3:24 p.m. |
| PD | Predicate disambiguation | batch_69d9150e85348190b9b47cda4a17dcd0 |
completed | April 10, 2026, 3:19 p.m. |
Created at: April 8, 2026, 9:50 p.m.