Triple
T34632347
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | rock sculpture of Decebalus near Orșova |
E889321
|
entity |
| Predicate | languageOfNearbyInscriptions |
P15804
|
FINISHED |
| Object | Latin |
—
|
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: Latin | Statement: [rock sculpture of Decebalus near Orșova, languageOfNearbyInscriptions, Latin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageOfNearbyInscriptions Context triple: [rock sculpture of Decebalus near Orșova, languageOfNearbyInscriptions, Latin]
-
A.
secondaryLanguageOfInscriptions
Indicates that a specified language serves as the secondary language used in the inscriptions associated with a given entity.
-
B.
inscriptionsLanguage
chosen
Indicates that the language used in the inscriptions on an object or surface is the specified language.
-
C.
officialLanguageOfInscriptions
Indicates the language officially used in the inscriptions associated with a particular entity.
-
D.
languageAttestedIn
Indicates that evidence exists showing the use or presence of a particular language in a specified place, time, or context.
-
E.
languageOfHistoricalRecord
Indicates the language in which a given historical record is written or recorded.
- 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_69f349d724848190b63ad3407e0006d9 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a0076c0a5c4819088b17b95511b93ed |
completed | May 10, 2026, 12:14 p.m. |
| PD | Predicate disambiguation | batch_6a007638a67c81909c091335142260ab |
completed | May 10, 2026, 12:12 p.m. |
Created at: May 1, 2026, 2:04 a.m.