Triple
T34019954
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ambassador of France to Austria |
E872354
|
entity |
| Predicate | representsInCity |
P198837
|
FINISHED |
| Object | Vienna |
E7023
|
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: Vienna | Statement: [Ambassador of France to Austria, representsInCity, Vienna]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: representsInCity Context triple: [Ambassador of France to Austria, representsInCity, Vienna]
-
A.
representsCity
Indicates that one entity serves as the official representative or embodiment of a particular city.
-
B.
representsCityOrTown
Indicates that one entity is a city or town that serves as a representative or exemplar of another entity (such as a region, organization, or concept).
-
C.
cityRepresented
Indicates that one entity serves as the official representative or governing body for a particular city.
-
D.
cityRepresentation
Indicates that one entity serves as the official or primary representative (such as a government, organization, or office) for a particular city in some context.
-
E.
representedCity
Indicates that an entity serves as the official representative or proxy for a particular city.
- F. None of above. chosen
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_69f349a19ad88190ab586f010c804a8f |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69ff0d80c0dc81909fbd12285c7a45c0 |
completed | May 9, 2026, 10:33 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a36cc6b049481908cb0f0c14bf9dd0d |
completed | June 20, 2026, 5:22 p.m. |
| PD | Predicate disambiguation | batch_69ff0cd03e78819094895058f925fbfa |
completed | May 9, 2026, 10:30 a.m. |
| PDg | Predicate description generation | batch_69ff0d800ee88190835e233d9e846cdb |
completed | May 9, 2026, 10:33 a.m. |
Created at: May 1, 2026, 1:51 a.m.