Triple
T2360603
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Levant region |
E47261
|
entity |
| Predicate | hasLanguageFamilyHistorically |
P11719
|
FINISHED |
| Object | Semitic languages |
—
|
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: Semitic languages | Statement: [Levant region, hasLanguageFamilyHistorically, Semitic languages]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLanguageFamilyHistorically Context triple: [Levant region, hasLanguageFamilyHistorically, Semitic languages]
-
A.
derivedFromLanguageFamily
Indicates that one language originates from, or historically descends from, a particular language family.
-
B.
hasLinguisticHeritage
chosen
Indicates that one entity possesses or is associated with the linguistic background, tradition, or ancestry of another entity.
-
C.
influencedLanguageFamily
Indicates that one language family has had a significant impact on the development, structure, or usage of another language family.
-
D.
hasMajorityLanguageHistorically
Indicates that a particular language has historically been the predominant or majority language within a given entity or region.
-
E.
languageFamilyBranchOf
Indicates that one language family branch is a sub-group or subdivision within a larger language family.
- 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_69a88a1a4a6081908645b0f2914521ab |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abc722ac3c819091f4316a4a166a77 |
completed | March 7, 2026, 6:35 a.m. |
| PD | Predicate disambiguation | batch_69abc599b92c819093d9e15d4437705d |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:55 p.m.