Triple
T24836268
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | historic center of Arles |
E621480
|
entity |
| Predicate | UNESCOSiteNameInFrench |
P13745
|
FINISHED |
| Object | Arles, monuments romains et romans |
—
|
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: Arles, monuments romains et romans | Statement: [historic center of Arles, UNESCOSiteNameInFrench, Arles, monuments romains et romans]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: UNESCOSiteNameInFrench Context triple: [historic center of Arles, UNESCOSiteNameInFrench, Arles, monuments romains et romans]
-
A.
UNESCOSiteNameLanguage
Indicates the language in which a UNESCO site’s name is expressed.
-
B.
officialNameUNESCO
chosen
Indicates the official name of an entity as recognized or designated by UNESCO.
-
C.
isFrancophoneCounterpartOf
Indicates that one entity serves as the French-speaking or French-language equivalent or counterpart of another entity.
-
D.
majorInscriptionSite
Indicates that a location serves as a primary or significant site where inscriptions are prominently found or produced.
-
E.
UNESCOWorldHeritageCentreURL
Indicates that there is a specific URL linking an entity to its page on the UNESCO World Heritage Centre website.
- 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_69e2fac185d48190a0a6073ad1f6b792 |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f48b9b687881908fd87a2f5fa0b1e7 |
completed | May 1, 2026, 11:16 a.m. |
| PD | Predicate disambiguation | batch_69f48060597c8190a4414e4e4fcb1fec |
completed | May 1, 2026, 10:28 a.m. |
Created at: April 18, 2026, 5:17 a.m.