Triple
T37397341
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Second Mass of Christmas (Roman Rite, traditional) |
E928888
|
entity |
| Predicate | hasStationChurch |
P202381
|
FINISHED |
| Object | Basilica of Saint Anastasia on the Palatine Hill |
—
|
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: Basilica of Saint Anastasia on the Palatine Hill | Statement: [Second Mass of Christmas (Roman Rite, traditional), hasStationChurch, Basilica of Saint Anastasia on the Palatine Hill]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasStationChurch Context triple: [Second Mass of Christmas (Roman Rite, traditional), hasStationChurch, Basilica of Saint Anastasia on the Palatine Hill]
-
A.
hasChurch
Indicates that a place or entity possesses, contains, or is associated with a church.
-
B.
hasStationAt
Indicates that an entity maintains or operates a station located at a specified place.
-
C.
hasChurchType
Indicates that one entity (typically a church) is classified as being of a particular church type or category.
-
D.
hasReplicaChurch
Indicates that an entity has a church that is a replica or reproduction of it.
-
E.
hasNumberOfChurches
Indicates the relationship that specifies how many churches are associated with a given entity.
- F. None of above. chosen
Provenance (4 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_69f76ebb10c481909b54b9dba263e29f |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a00781b749c8190921c46e110cae0b0 |
completed | May 10, 2026, 12:20 p.m. |
| PD | Predicate disambiguation | batch_6a0077df3c8481909fabc9e84f5936e3 |
completed | May 10, 2026, 12:19 p.m. |
| PDg | Predicate description generation | batch_6a00781ac0f48190a77e2c326a4d6693 |
completed | May 10, 2026, 12:20 p.m. |
Created at: May 3, 2026, 4:16 p.m.