Triple
T26830790
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oxford reserve crews |
E675493
|
entity |
| Predicate | opponentCrew |
P116577
|
FINISHED |
| Object |
Blondie (Cambridge women’s reserve crew)
Blondie is the Cambridge University women’s reserve rowing crew that competes against Oxford’s reserve crews in the annual Boat Race.
|
E1744594
|
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: Blondie (Cambridge women’s reserve crew) | Statement: [Oxford reserve crews, opponentCrew, Blondie (Cambridge women’s reserve crew)]
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: Blondie (Cambridge women’s reserve crew) Triple: [Oxford reserve crews, opponentCrew, Blondie (Cambridge women’s reserve crew)]
Generated description
Blondie is the Cambridge University women’s reserve rowing crew that competes against Oxford’s reserve crews in the annual Boat Race.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: opponentCrew Context triple: [Oxford reserve crews, opponentCrew, Blondie (Cambridge women’s reserve crew)]
-
A.
opponentGroup
chosen
Indicates that one group is in opposition or conflict with another group, typically as a rival, competitor, or adversary.
-
B.
captainOpponent
Indicates that one entity serves as the captain or leader of a team that is competing against the other entity.
-
C.
opponentFleet
Indicates that one fleet is in an adversarial or opposing relationship to another fleet.
-
D.
opposingAlliance
Indicates that two entities belong to rival or mutually opposed alliances or factions.
-
E.
opponentStarPlayerTeam
Indicates that the referenced team is the one for which the opponent’s star player plays.
- 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_69eee9b776448190993a60b67fcc9545 |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69f6247480cc8190a887eedaeb94615c |
completed | May 2, 2026, 4:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a12133f1288819080577fff0c3b9681 |
completed | May 23, 2026, 8:51 p.m. |
| NEDg | Description generation | batch_6a1215655aac8190b3f1a131550befc2 |
completed | May 23, 2026, 9 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a1216420ef08190b33368157a089c98 |
completed | May 23, 2026, 9:04 p.m. |
| PD | Predicate disambiguation | batch_69f623a7539c8190b71797f583da9f63 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 5:01 a.m.