Triple
T26116456
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Etihad First Apartments |
E658835
|
entity |
| Predicate | awardRedemption |
P40855
|
FINISHED |
| Object | bookable with Etihad Guest miles |
—
|
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: bookable with Etihad Guest miles | Statement: [Etihad First Apartments, awardRedemption, bookable with Etihad Guest miles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: awardRedemption Context triple: [Etihad First Apartments, awardRedemption, bookable with Etihad Guest miles]
-
A.
rewardRedemption
chosen
Indicates the act of exchanging accumulated rewards, points, or benefits for goods, services, or other forms of value.
-
B.
awardCurrency
Indicates that one entity grants or gives a specified amount of currency to another entity.
-
C.
returnedAward
Indicates that an entity has given back or relinquished a previously received award to the awarding party or institution.
-
D.
grantedAsRewardFor
Indicates that something is given to an entity specifically as a reward for a particular action, achievement, or service.
-
E.
awardEffect
Indicates that one entity confers or grants a benefit, recognition, or reward that has a particular impact or consequence on 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_69ee5bc20298819099a42be042eb2349 |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69f65f7731e4819099d5bd3d915ee266 |
completed | May 2, 2026, 8:32 p.m. |
| PD | Predicate disambiguation | batch_69f65c1f94ac8190bc6fbc7916fc0d82 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 26, 2026, 8:05 p.m.