Triple
T38628035
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Concattedrale Gran Madre di Dio |
E937368
|
entity |
| Predicate | nativeName |
P15
|
FINISHED |
| Object |
Concattedrale Gran Madre di Dio
Concattedrale Gran Madre di Dio is a Roman Catholic co-cathedral in Italy dedicated to Our Lady, serving as an important local center of worship and diocesan liturgy.
|
E2279633
|
NE 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: Concattedrale Gran Madre di Dio | Statement: [Concattedrale Gran Madre di Dio, nativeName, Concattedrale Gran Madre di Dio]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Concattedrale Gran Madre di Dio Triple: [Concattedrale Gran Madre di Dio, nativeName, Concattedrale Gran Madre di Dio]
Generated description
Concattedrale Gran Madre di Dio is a Roman Catholic co-cathedral in Italy dedicated to Our Lady, serving as an important local center of worship and diocesan liturgy.
Provenance (5 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_69f76ed5ca3c81909288f61fbf37b359 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fcd99865148190af64530a207bac2c |
completed | May 7, 2026, 6:27 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a41fd56ae00819085f26cb8a50e9823 |
completed | June 29, 2026, 5:06 a.m. |
| NEDg | Description generation | batch_6a41fe94c1fc8190bb21fee5acc371ff |
completed | June 29, 2026, 5:11 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a41ff1ca2d481909286a6c77f64b8b1 |
completed | June 29, 2026, 5:14 a.m. |
Created at: May 3, 2026, 4:32 p.m.