Triple
T33653202
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KrisFlyer Elite Gold |
E862152
|
entity |
| Predicate | checkInCounterAccess |
P24791
|
FINISHED |
| Object | business class counters on many flights |
—
|
LITERAL FINISHED |
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: business class counters on many flights | Statement: [KrisFlyer Elite Gold, checkInCounterAccess, business class counters on many flights]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: checkInCounterAccess Context triple: [KrisFlyer Elite Gold, checkInCounterAccess, business class counters on many flights]
-
A.
hasCheckInCounters
chosen
Indicates that an entity is associated with one or more check-in counters used for processing arrivals or registrations.
-
B.
checkInTime
Indicates the time at which an entity arrives at and formally registers its presence at a specified place or event.
-
C.
checksInto
Indicates that one entity formally registers its arrival at or entry into another entity, such as a place, event, or system.
-
D.
hasCheckInSystem
Indicates that an entity uses or is equipped with a system for registering or recording check-ins.
-
E.
hasCheckoutCounter
Indicates that one entity possesses or includes a checkout counter used for processing purchases or transactions.
- 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_69f349840ba881908e3bfce536aeb92b |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6fb19063c81909466b329655c8583 |
completed | May 3, 2026, 7:36 a.m. |
| PD | Predicate disambiguation | batch_69f6f96badb08190994442c2aba840b1 |
completed | May 3, 2026, 7:29 a.m. |
Created at: May 1, 2026, 1:42 a.m.