Triple
T25969616
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2019 NCAA Division I men's basketball tournament |
E645768
|
entity |
| Predicate | eastRegionalCity |
P159618
|
FINISHED |
| Object | Washington, D.C. |
—
|
NE NERFINISHED |
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: Washington, D.C. | Statement: [2019 NCAA Division I men's basketball tournament, eastRegionalCity, Washington, D.C.]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eastRegionalCity Context triple: [2019 NCAA Division I men's basketball tournament, eastRegionalCity, Washington, D.C.]
-
A.
servesAsFocusCityFor
Indicates that a city functions as a primary or designated focus city for an airline, organization, or transportation network, typically hosting significant but not hub-level operations or activities.
-
B.
city1
Indicates that the subject is classified as a city.
-
C.
cityOn
Indicates that a city is geographically located on a specified landform, area, or administrative region.
-
D.
isSuburbanCityOf
Indicates that one city is a suburban municipality that is part of, or closely associated with, a larger primary city or metropolitan area.
-
E.
nearestLargeCityNorth
Indicates that one city is the closest large city located to the north of another 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_69e77e8768648190b27bb578f14bcb88 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f604cd91088190a2c9ab800dcaec37 |
completed | May 2, 2026, 2:06 p.m. |
| PD | Predicate disambiguation | batch_69f4a10480748190a2e67bd399fc435d |
completed | May 1, 2026, 12:48 p.m. |
| PDg | Predicate description generation | batch_69f55e497fa081909bc59a7b92c5df59 |
completed | May 2, 2026, 2:15 a.m. |
Created at: April 22, 2026, 8:50 a.m.