Triple
T38549786
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2022 NCAA Men’s Final Four |
E925073
|
entity |
| Predicate | semifinalistSeed |
P18175
|
FINISHED |
| Object |
No. 2 seed Duke
No. 2 seed Duke refers to the Duke Blue Devils men's basketball team, a powerhouse NCAA program that entered the 2022 tournament as a No. 2 seed and advanced to the Final Four.
|
E2274211
|
NE FINISHED |
How this triple was built (3 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: No. 2 seed Duke | Statement: [2022 NCAA Men’s Final Four, semifinalistSeed, No. 2 seed Duke]
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: No. 2 seed Duke Triple: [2022 NCAA Men’s Final Four, semifinalistSeed, No. 2 seed Duke]
Generated description
No. 2 seed Duke refers to the Duke Blue Devils men's basketball team, a powerhouse NCAA program that entered the 2022 tournament as a No. 2 seed and advanced to the Final Four.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: semifinalistSeed Context triple: [2022 NCAA Men’s Final Four, semifinalistSeed, No. 2 seed Duke]
-
A.
topSeedByeToSemifinals
Indicates that the top-seeded participant automatically advances directly to the semifinals without playing earlier rounds.
-
B.
semifinalist
Indicates that an entity has advanced to the semifinal round or stage of a competition, selection process, or tournament.
-
C.
playoffSeed
chosen
Indicates the ranking or position a team or player holds in a playoff bracket based on their performance or qualification criteria.
-
D.
secondSeedByeToSemifinals
Indicates that the competitor seeded second advances directly to the semifinals without having to play in earlier rounds (a bye).
-
E.
semifinalResult
Indicates the outcome or score of a semifinal-stage contest or match between competitors.
- F. None of above.
Provenance (6 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_69f76eaeb69c8190b367df9330d6f6af |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fcd3163d0881909d3209cd7cb81c10 |
completed | May 7, 2026, 5:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a41e03bcfe88190a85e65bfab80301d |
completed | June 29, 2026, 3:02 a.m. |
| NEDg | Description generation | batch_6a41e15c67ac8190b877a4bfd4e7499c |
completed | June 29, 2026, 3:07 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a41e1d6985081909748d210df210c84 |
completed | June 29, 2026, 3:09 a.m. |
| PD | Predicate disambiguation | batch_69fcd1f81cbc8190b4fd3bfc3106c1f3 |
completed | May 7, 2026, 5:55 p.m. |
Created at: May 3, 2026, 4:32 p.m.