Triple
T36717589
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Barbarian F.C. |
E906955
|
entity |
| Predicate | famousFixture |
P18798
|
FINISHED |
| Object | Barbarians vs New Zealand, Cardiff, 27 January 1973 |
—
|
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: Barbarians vs New Zealand, Cardiff, 27 January 1973 | Statement: [Barbarian F.C., famousFixture, Barbarians vs New Zealand, Cardiff, 27 January 1973]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: famousFixture Context triple: [Barbarian F.C., famousFixture, Barbarians vs New Zealand, Cardiff, 27 January 1973]
-
A.
famousMatch
chosen
Indicates that two entities are linked by a match or pairing that is widely known or celebrated.
-
B.
primaryKeyInFamousSet
Indicates that an entity serves as the main identifying key within a designated set of notable or famous entities.
-
C.
famousInitiate
Indicates that an entity initiates or starts an action, event, or process in a way that is widely recognized or notable.
-
D.
famousModel
Indicates that the subject is a well-known or widely recognized model.
-
E.
famousLegend
Indicates that the subject is widely known and celebrated in stories, myths, or folklore, often with enduring cultural significance.
- F. None of above.
Provenance (3 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_69f76e73ad108190a5241585f2303e9a |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f7c841388481909a408b704b30f9c7 |
completed | May 3, 2026, 10:12 p.m. |
| PD | Predicate disambiguation | batch_69f7c4796ebc819084a0dc08505e5f14 |
completed | May 3, 2026, 9:56 p.m. |
Created at: May 3, 2026, 4:12 p.m.