Triple
T9274188
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | sanctuary of Herentas |
E222902
|
entity |
| Predicate | inscriptionLanguageEvidence |
P15804
|
FINISHED |
| Object | Oscan |
—
|
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: Oscan | Statement: [sanctuary of Herentas, inscriptionLanguageEvidence, Oscan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inscriptionLanguageEvidence Context triple: [sanctuary of Herentas, inscriptionLanguageEvidence, Oscan]
-
A.
hasLanguageEvidenceOf
Indicates that there is linguistic or textual evidence supporting, documenting, or attesting to the related entity or claim.
-
B.
languageOfAttestation
Indicates the language in which a statement, document, or evidence is originally recorded or attested.
-
C.
signatureLanguage
Indicates the language in which a signature (e.g., on a document or agreement) is written or expressed.
-
D.
inscriptionTranslation
Indicates that a provided text expresses the translated content of a specific inscription.
-
E.
inscriptionsLanguage
chosen
Indicates that the language used in the inscriptions on an object or surface is the specified language.
- 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_69ca841ffe208190aa7bcffbef2f8379 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd0788e87c81909ccda40d94cc6705 |
completed | April 1, 2026, 11:54 a.m. |
| PD | Predicate disambiguation | batch_69cc7a537bbc8190baee71f556e52a7b |
completed | April 1, 2026, 1:52 a.m. |
Created at: March 30, 2026, 7:33 p.m.