Triple
T24001080
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | مصرف لبنان |
E594249
|
entity |
| Predicate | الاسم_باللغة_الفرنسية |
P6538
|
FINISHED |
| Object | Banque du Liban |
—
|
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: Banque du Liban | Statement: [مصرف لبنان, الاسم_باللغة_الفرنسية, Banque du Liban]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: الاسم_باللغة_الفرنسية Context triple: [مصرف لبنان, الاسم_باللغة_الفرنسية, Banque du Liban]
-
A.
nameInFrench
chosen
Indicates that an entity is known or referred to by a specific name expressed in the French language.
-
B.
isFrancophoneCounterpartOf
Indicates that one entity serves as the French-speaking or French-language equivalent or counterpart of another entity.
-
C.
alternateLanguageName
Indicates that an entity has an additional name or label in a different language from its primary or default name.
-
D.
nameInOriginalLanguage
Indicates that an entity’s name is given in its original or native language form.
-
E.
equivalentTitleInFrench
Indicates that one entity’s title is the equivalent or corresponding title of another entity, specifically expressed in French.
- 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_69e288b9ecf08190b8c94a278f5674fe |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1d464f1988190a0a9352c1ec214eb |
completed | April 29, 2026, 9:50 a.m. |
| PD | Predicate disambiguation | batch_69f1615994c48190a5de95d3f7e5cd0a |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 9:39 p.m.