Triple
T32902471
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Song to the Evening Star |
E841647
|
entity |
| Predicate | firstPerformanceLocationOpera |
P105282
|
FINISHED |
| Object | Dresden |
E37454
|
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: Dresden | Statement: [Song to the Evening Star, firstPerformanceLocationOpera, Dresden]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstPerformanceLocationOpera Context triple: [Song to the Evening Star, firstPerformanceLocationOpera, Dresden]
-
A.
firstPerformanceOpera
Indicates the relationship in which an opera work is presented in its first-ever performance.
-
B.
firstPerformanceInOpera
chosen
Indicates that an entity’s first-ever performance occurred in the context of an opera production.
-
C.
firstPerformanceTheatreWithOpera
Indicates that a theatre hosted its first performance that included an opera.
-
D.
firstPerformanceOperaTitle
Indicates the title of the opera in which a given performance was the first performance.
-
E.
firstPerformanceOperaYear
Indicates the year in which an opera was first performed.
- F. None of above.
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_69f34946a5208190bbd79f0fec4323bd |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_6a037cad051c8190b28b354b89208574 |
completed | May 12, 2026, 7:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3576c98c0c81909ec8bcdabe6ece38 |
completed | June 19, 2026, 5:05 p.m. |
| PD | Predicate disambiguation | batch_6a0379f0cbe481909b4b8fc6cbe297f0 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 1:19 a.m.