Triple
T4397047
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GUM department store |
E99515
|
entity |
| Predicate | hasArcadeType |
P24796
|
FINISHED |
| Object | glass-roofed shopping arcade |
—
|
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: glass-roofed shopping arcade | Statement: [GUM department store, hasArcadeType, glass-roofed shopping arcade]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasArcadeType Context triple: [GUM department store, hasArcadeType, glass-roofed shopping arcade]
-
A.
hasArcades
chosen
Indicates that one entity features or contains arcaded structures (a series of arches or covered passageways) associated with another entity.
-
B.
hasGameType
Indicates that an entity (such as a game or match) is associated with a specific category or type of game.
-
C.
includesGameType
Indicates that one entity contains or supports a particular type or category of game.
-
D.
hasCasino
Indicates that an entity includes, contains, or is associated with a casino facility or gambling establishment.
-
E.
hasAttractionType
Indicates that one entity is associated with a specific kind or category of attraction (e.g., tourist, cultural, natural).
- 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_69b345506b408190b0e3dee616738a7d |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b352aca86c8190b5af7e6600072066 |
completed | March 12, 2026, 11:56 p.m. |
| PD | Predicate disambiguation | batch_69b34f597998819092477efdedb51427 |
completed | March 12, 2026, 11:42 p.m. |
Created at: March 12, 2026, 11:20 p.m.