Triple
T28249548
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MQDs |
E712275
|
entity |
| Predicate | appliesToCustomerType |
P89928
|
FINISHED |
| Object | SkyMiles members |
E36412
|
NE 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: SkyMiles members | Statement: [MQDs, appliesToCustomerType, SkyMiles members]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appliesToCustomerType Context triple: [MQDs, appliesToCustomerType, SkyMiles members]
-
A.
appliesToPersonType
Indicates that something (such as a rule, condition, or attribute) is relevant or applicable specifically to a certain type or category of person.
-
B.
appliesToPartyType
chosen
Indicates that a rule, condition, or attribute is relevant to and affects a specific type or category of party (such as an individual, organization, or group).
-
C.
appliesToProductType
Indicates that something (such as a rule, offer, or condition) is relevant or applicable specifically to a certain type or category of product.
-
D.
appliesToServiceType
Indicates that something is relevant or applicable specifically to a particular type or category of service.
-
E.
appliesToRevenueType
Indicates that a rule, condition, or classification is specifically relevant or applicable to a particular type of revenue.
- F. None of above.
Provenance (4 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_69efb51fb98881909692421959ec0170 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69fcdf2394748190b35cead3e208447d |
completed | May 7, 2026, 6:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a15e6d7e6b88190b525d8f9dba3944c |
completed | May 26, 2026, 6:30 p.m. |
| PD | Predicate disambiguation | batch_69fcdbe344ec8190a0471911952f4b82 |
completed | May 7, 2026, 6:37 p.m. |
Created at: April 27, 2026, 11:03 p.m.