Triple
T34981369
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paul (Die tote Stadt) |
E1008822
|
entity |
| Predicate | housekeeper |
P68145
|
FINISHED |
| Object |
Brigitta (Die tote Stadt)
Brigitta is the devout and loyal housekeeper in Erich Wolfgang Korngold’s opera "Die tote Stadt," serving as a moral and emotional counterpoint to the protagonist Paul.
|
E2123404
|
NE FINISHED |
How this triple was built (3 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: Brigitta (Die tote Stadt) | Statement: [Paul (Die tote Stadt), housekeeper, Brigitta (Die tote Stadt)]
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: Brigitta (Die tote Stadt) Triple: [Paul (Die tote Stadt), housekeeper, Brigitta (Die tote Stadt)]
Generated description
Brigitta is the devout and loyal housekeeper in Erich Wolfgang Korngold’s opera "Die tote Stadt," serving as a moral and emotional counterpoint to the protagonist Paul.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: housekeeper Context triple: [Paul (Die tote Stadt), housekeeper, Brigitta (Die tote Stadt)]
-
A.
householdStaff
chosen
Indicates that one entity serves as domestic or household staff for another entity, typically within a private residence.
-
B.
housekeeperPraises
Indicates that a housekeeper expresses approval or commendation toward someone or something.
-
C.
household
Indicates that two or more entities belong to or are part of the same household unit, typically sharing a residence and domestic life.
-
D.
houseRole
Indicates the functional role, purpose, or use that a house has within a given context or system.
-
E.
houseHead
Indicates that one entity serves as the head, leader, or primary authority of a particular house or household associated with the other entity.
- F. None of above.
Provenance (6 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_69f76dc844a48190881951fffb83d17e |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f78ce78b508190955848e133398dc8 |
completed | May 3, 2026, 5:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a37c623f9cc81908213ceb2e8be7ef2 |
completed | June 21, 2026, 11:08 a.m. |
| NEDg | Description generation | batch_6a37c6a375b08190a4fed21a96ca40d3 |
completed | June 21, 2026, 11:10 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a37c73c47b08190a691c8afb098a9f3 |
completed | June 21, 2026, 11:13 a.m. |
| PD | Predicate disambiguation | batch_69f78b8f4cc08190b49fccd798cb25d7 |
completed | May 3, 2026, 5:53 p.m. |
Created at: May 3, 2026, 4:01 p.m.