Triple
T9240456
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aeroport |
E222043
|
entity |
| Predicate | nearbyArea |
P2064
|
FINISHED |
| Object |
Khodynka Field
Khodynka Field is a historic area in Moscow known for its former airfield, major public events, and the tragic 1896 coronation stampede.
|
E787050
|
NE FINISHED |
How this triple was built (4 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: Khodynka Field | Statement: [Aeroport, nearbyArea, Khodynka Field]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Khodynka Field Context triple: [Aeroport, nearbyArea, Khodynka Field]
-
A.
Krenzler Field
Krenzler Field is a soccer stadium in Portland, Oregon, serving as the home venue for the Portland State Vikings soccer teams.
-
B.
White Stadium
White Stadium is an outdoor sports venue in Boston, Massachusetts, primarily used for football and other athletic events.
-
C.
Crocus Field
Crocus Field is the historic battlefield in ancient Thessaly, Greece, where Philip II of Macedon decisively defeated the Phocians during the Third Sacred War.
-
D.
Dooley Field
Dooley Field is the playing surface at the University of Georgia’s Sanford Stadium, named in honor of legendary Bulldogs football coach and athletic director Vince Dooley.
-
E.
Berman Field
Berman Field is a soccer stadium at Cornell University in Ithaca, New York, primarily used for collegiate soccer matches.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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: Khodynka Field Triple: [Aeroport, nearbyArea, Khodynka Field]
Generated description
Khodynka Field is a historic area in Moscow known for its former airfield, major public events, and the tragic 1896 coronation stampede.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Khodynka Field Target entity description: Khodynka Field is a historic area in Moscow known for its former airfield, major public events, and the tragic 1896 coronation stampede.
-
A.
Krenzler Field
Krenzler Field is a soccer stadium in Portland, Oregon, serving as the home venue for the Portland State Vikings soccer teams.
-
B.
White Stadium
White Stadium is an outdoor sports venue in Boston, Massachusetts, primarily used for football and other athletic events.
-
C.
Crocus Field
Crocus Field is the historic battlefield in ancient Thessaly, Greece, where Philip II of Macedon decisively defeated the Phocians during the Third Sacred War.
-
D.
Dooley Field
Dooley Field is the playing surface at the University of Georgia’s Sanford Stadium, named in honor of legendary Bulldogs football coach and athletic director Vince Dooley.
-
E.
Berman Field
Berman Field is a soccer stadium at Cornell University in Ithaca, New York, primarily used for collegiate soccer matches.
- 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_69ca83ee26cc81909ac624e190597d6d |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccf0a3888c8190b72d8d0b850bdfbc |
completed | April 1, 2026, 10:17 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d077db03048190b9c1f0812da21733 |
completed | April 4, 2026, 2:30 a.m. |
| NEDg | Description generation | batch_69d07dc19c2881909f095db0659f54db |
completed | April 4, 2026, 2:56 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d07e0ff9188190ba4b9c4ad17d37f5 |
completed | April 4, 2026, 2:57 a.m. |
Created at: March 30, 2026, 7:30 p.m.