Triple
T16854660
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Unified Ad Marketplace |
E409752
|
entity |
| Predicate | auctionType |
P77215
|
FINISHED |
| Object | first-price auction |
—
|
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: first-price auction | Statement: [Unified Ad Marketplace, auctionType, first-price auction]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: auctionType Context triple: [Unified Ad Marketplace, auctionType, first-price auction]
-
A.
auctionMethod
chosen
Indicates the type or procedure of auction used to conduct a sale or bidding process between parties.
-
B.
auctionCategory
Indicates that an item is classified under a specific auction category or type within an auction system.
-
C.
auctionRecord
Indicates that there exists a documented record of an auction event involving the related entities.
-
D.
auctionContext
Indicates that an entity participates in or is associated with an auction-related situation, including its rules, conditions, or surrounding circumstances.
-
E.
auctionPresence
Indicates that an entity participates in, is present at, or is involved with a particular auction event.
- 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_69d88395e6c88190b22730f335107c14 |
completed | April 10, 2026, 4:59 a.m. |
| NER | Named-entity recognition | batch_69e3b37c6e808190975b14b228253029 |
completed | April 18, 2026, 4:38 p.m. |
| PD | Predicate disambiguation | batch_69e32b8cbb048190878a259cc5be960e |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:24 a.m.