Triple
T33677442
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Copa ConnectMiles Silver |
E862798
|
entity |
| Predicate | tierRankBelow |
P32836
|
FINISHED |
| Object | Copa ConnectMiles Gold |
—
|
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: Copa ConnectMiles Gold | Statement: [Copa ConnectMiles Silver, tierRankBelow, Copa ConnectMiles Gold]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tierRankBelow Context triple: [Copa ConnectMiles Silver, tierRankBelow, Copa ConnectMiles Gold]
-
A.
lowerRank
Indicates that one entity holds an inferior or subordinate rank, status, or position relative to another entity.
-
B.
rankTier
Indicates the classification level or tier assigned to an entity within a ranking or hierarchical system.
-
C.
lowerRankedOrder
Indicates that one entity holds a lower rank or priority in an ordered sequence relative to another entity.
-
D.
lowestRank
Indicates that the subject has the least or worst rank in an ordered set compared to all other related entities.
-
E.
hasLowerTier
chosen
Indicates that one entity is ranked, valued, or classified at a lower level or tier relative to another entity.
- 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_69f34985885c8190914322f492e04703 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6fa4078a88190a0851bdcae68f2ea |
completed | May 3, 2026, 7:33 a.m. |
| PD | Predicate disambiguation | batch_69f6f96dd4c8819093d6a7bd046a9ad5 |
completed | May 3, 2026, 7:29 a.m. |
Created at: May 1, 2026, 1:43 a.m.