Triple
T3988130
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stele of Novilara |
E86921
|
entity |
| Predicate | inscriptionLength |
P266
|
FINISHED |
| Object | relatively long text for North Picene |
—
|
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: relatively long text for North Picene | Statement: [Stele of Novilara, inscriptionLength, relatively long text for North Picene]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inscriptionLength Context triple: [Stele of Novilara, inscriptionLength, relatively long text for North Picene]
-
A.
identifierLength
Indicates the length or number of characters in an entity’s identifier.
-
B.
IVLength
Indicates the measured length of an intravenous (IV) line or catheter used in a medical context.
-
C.
inscriptionCompleteness
Indicates how fully or partially an inscription is preserved or recorded in relation to its original state.
-
D.
length
chosen
Indicates a measurement relationship where a value specifies how long something is from one end to the other.
-
E.
inscriptionType
Indicates the specific kind or category of inscription associated with an entity (e.g., dedicatory, funerary, commemorative).
- 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_69aed93fd9d4819085d3b2137d2346cb |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefb81040481909b22e4c445ecae0f |
completed | March 9, 2026, 4:55 p.m. |
| PD | Predicate disambiguation | batch_69aef8f692008190bf4d637ffc3d3eaa |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:33 p.m.