Triple
T109071
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1994 Winter Olympics |
E2202
|
entity |
| Predicate | usedVenue |
P373
|
FINISHED |
| Object |
Kristins Hall
Kristins Hall is an indoor ice arena in Lillehammer, Norway, best known for hosting ice hockey events during the 1994 Winter Olympics.
|
E17180
|
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: Kristins Hall | Statement: [1994 Winter Olympics, usedVenue, Kristins Hall]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kristins Hall Context triple: [1994 Winter Olympics, usedVenue, Kristins Hall]
-
A.
Håkons Hall
Håkons Hall is a large multi-purpose indoor arena in Lillehammer, Norway, best known for hosting ice hockey events during the 1994 Winter Olympics.
-
B.
Kingdom Hall
Kingdom Hall is the name given to the local meeting places used by Jehovah’s Witnesses for their congregational worship and religious activities.
-
C.
Matthews Hall
Matthews Hall is a historic red-brick freshman dormitory at Harvard University, located in Harvard Yard.
-
D.
Straus Hall
Straus Hall is an undergraduate dormitory in Harvard Yard at Harvard University, known for housing first-year students.
-
E.
Lavietes Pavilion
Lavietes Pavilion is an indoor basketball arena at Harvard University that serves as the home court for the Harvard Crimson basketball teams.
- 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: Kristins Hall Triple: [1994 Winter Olympics, usedVenue, Kristins Hall]
Generated description
Kristins Hall is an indoor ice arena in Lillehammer, Norway, best known for hosting ice hockey events during the 1994 Winter Olympics.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Kristins Hall Target entity description: Kristins Hall is an indoor ice arena in Lillehammer, Norway, best known for hosting ice hockey events during the 1994 Winter Olympics.
-
A.
Håkons Hall
Håkons Hall is a large multi-purpose indoor arena in Lillehammer, Norway, best known for hosting ice hockey events during the 1994 Winter Olympics.
-
B.
Kingdom Hall
Kingdom Hall is the name given to the local meeting places used by Jehovah’s Witnesses for their congregational worship and religious activities.
-
C.
Matthews Hall
Matthews Hall is a historic red-brick freshman dormitory at Harvard University, located in Harvard Yard.
-
D.
Straus Hall
Straus Hall is an undergraduate dormitory in Harvard Yard at Harvard University, known for housing first-year students.
-
E.
Lavietes Pavilion
Lavietes Pavilion is an indoor basketball arena at Harvard University that serves as the home court for the Harvard Crimson basketball teams.
- 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_69a24fcdaeb48190a2d796677e4b3281 |
completed | Feb. 28, 2026, 2:15 a.m. |
| NER | Named-entity recognition | batch_69a25b7e2c188190b1dd8aafd4507a99 |
completed | Feb. 28, 2026, 3:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a2bf6620c88190bfc1c65b9942c98f |
completed | Feb. 28, 2026, 10:11 a.m. |
| NEDg | Description generation | batch_69a2c108b6388190b25564c8cdb01e4b |
completed | Feb. 28, 2026, 10:18 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a2c16e930881909281ba41d5da303b |
completed | Feb. 28, 2026, 10:20 a.m. |
Created at: Feb. 28, 2026, 2:20 a.m.