Triple
T29342913
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Basilica of Santa Maria in Trastevere |
E744083
|
entity |
| Predicate | hasCivicAddress |
P4379
|
FINISHED |
| Object | Piazza di Santa Maria in Trastevere |
—
|
NE NERFINISHED |
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: Piazza di Santa Maria in Trastevere | Statement: [Basilica of Santa Maria in Trastevere, hasCivicAddress, Piazza di Santa Maria in Trastevere]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCivicAddress Context triple: [Basilica of Santa Maria in Trastevere, hasCivicAddress, Piazza di Santa Maria in Trastevere]
-
A.
hasCivicNumber
Indicates that an entity is associated with a specific civic (street) number used for its address.
-
B.
hasCivicIdentity
Indicates that an entity possesses a recognized status, role, or affiliation within a civic, social, or political community.
-
C.
hasCivicElements
Indicates that something includes or involves aspects related to civic life, responsibilities, or public affairs.
-
D.
hasAddressState
Indicates that an entity’s address is located within a particular state or state-level administrative region.
-
E.
hasAddress
chosen
Indicates that an entity is associated with a specific address or location.
- 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_69f09126cfcc8190899b16fbf3c2bf7b |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_69f6fb19063c81909466b329655c8583 |
completed | May 3, 2026, 7:36 a.m. |
| PD | Predicate disambiguation | batch_69f6f969b4cc8190afb473a2d8b110bc |
completed | May 3, 2026, 7:29 a.m. |
Created at: April 28, 2026, 1:34 p.m.