Triple
T1085331
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Seven Wonders of the Ancient World |
E24036
|
entity |
| Predicate | languageOfEarliestSources |
P2925
|
FINISHED |
| Object | Ancient Greek |
—
|
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: Ancient Greek | Statement: [Seven Wonders of the Ancient World, languageOfEarliestSources, Ancient Greek]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageOfEarliestSources Context triple: [Seven Wonders of the Ancient World, languageOfEarliestSources, Ancient Greek]
-
A.
languageOfEarliestForm
Indicates the language in which the earliest known form or attested version of something (e.g., a text, name, or expression) is recorded.
-
B.
languageOfSources
chosen
Indicates that the specified language is the language in which the referenced sources or source materials are expressed.
-
C.
historicallySpokenIn
Indicates that a language was used for spoken communication in a particular place or region during a past historical period.
-
D.
historicalLanguage
Indicates that one language is a historical or earlier form/ancestor of another language.
-
E.
hasLanguageOfOrigin
Indicates that one entity has its origin or source in the language specified by 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_69a49404428c819092dcc9632f5f7b8b |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4b961d0cc8190858296b44fab2f32 |
completed | March 1, 2026, 10:10 p.m. |
| PD | Predicate disambiguation | batch_69a4b7407914819092ed933a7316b450 |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:42 p.m.