Triple
T30253506
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ganjali Khan Complex |
E769272
|
entity |
| Predicate | containsCommercialBuilding |
P14728
|
FINISHED |
| Object | bazaar |
—
|
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: bazaar | Statement: [Ganjali Khan Complex, containsCommercialBuilding, bazaar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: containsCommercialBuilding Context triple: [Ganjali Khan Complex, containsCommercialBuilding, bazaar]
-
A.
containsBuilding
chosen
Indicates that one location or area includes a building within its boundaries.
-
B.
isCommercialFacility
Indicates that a facility is used primarily for commercial or business-related activities or services.
-
C.
appliesToBuildingComplex
Indicates that something (such as a rule, condition, attribute, or action) is relevant or applicable to an entire building complex rather than to individual buildings or units.
-
D.
hasCommercialInfrastructure
Indicates that an entity possesses or is equipped with facilities, systems, or structures that support commercial or business activities.
-
E.
isMajorOfficeBuildingIn
Indicates that a building is a primary or significant office structure located within a specified geographic or administrative area.
- 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_69f224831dc08190b2e569b987264057 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69fee335cb08819097e3a0e09d5ebf49 |
completed | May 9, 2026, 7:33 a.m. |
| PD | Predicate disambiguation | batch_69fee2c74fd88190acfc045ab07b7f6b |
completed | May 9, 2026, 7:31 a.m. |
Created at: April 29, 2026, 7:40 p.m.