Triple
T3155725
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paris–Los Angeles |
E65980
|
entity |
| Predicate | connectsTypeOfCity |
P46659
|
FINISHED |
| Object | national capital |
—
|
LITERAL 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: national capital | Statement: [Paris–Los Angeles, connectsTypeOfCity, national capital]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectsTypeOfCity Context triple: [Paris–Los Angeles, connectsTypeOfCity, national capital]
-
A.
connectsCity
Indicates a relationship where one entity serves as a link or route that joins or provides direct access between two cities.
-
B.
linkedCity
Indicates that two entities are associated with each other through a specific city, such as being located in, connected via, or related by that city.
-
C.
city2
Indicates a relationship where one entity is identified as a city associated with, located in, or otherwise linked to another entity.
-
D.
cityAssociatedWith
Indicates that there is a notable connection or relationship between a city and another entity, such as relevance, involvement, or contextual association.
-
E.
connectsCapitalCity
Indicates a relationship where an entity is linked or associated specifically with a capital city.
- 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_69ad8584485081909ed529e890cadc4a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada5e97548819084643586fff2e3cb |
completed | March 8, 2026, 4:38 p.m. |
| PD | Predicate disambiguation | batch_69ad9dfbf0348190952a6bca8fc5fed1 |
completed | March 8, 2026, 4:04 p.m. |
| PDg | Predicate description generation | batch_69ada1e4f7288190a80a1672e458132d |
completed | March 8, 2026, 4:20 p.m. |
Created at: March 8, 2026, 3:05 p.m.