Triple
T4974852
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shell |
E111738
|
entity |
| Predicate | hasRetailNetwork |
P60735
|
FINISHED |
| Object | global network of service stations |
—
|
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: global network of service stations | Statement: [Shell, hasRetailNetwork, global network of service stations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRetailNetwork Context triple: [Shell, hasRetailNetwork, global network of service stations]
-
A.
hasRetailPresenceIn
Indicates that an entity conducts retail operations or maintains a retail outlet, store, or sales presence within a specified location.
-
B.
hasRetailFormat
Indicates that one entity operates or is organized according to a particular retail format or store type.
-
C.
hasRetailBoutiquesIn
Indicates that an entity operates or maintains retail boutiques located within a specified place or region.
-
D.
hasRetailArea
Indicates that an entity possesses or includes a designated space used for retail or commercial sales activities.
-
E.
hasRetailCategory
Indicates that an entity is associated with a specific retail category or type of retail business.
- F. None of above. chosen
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_69bd441a0eb481908050fa4273b19eae |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd730a7590819088ab8d49c5c88c2f |
completed | March 20, 2026, 4:17 p.m. |
| PD | Predicate disambiguation | batch_69bd7146e6e881908a55ab2756b631f6 |
completed | March 20, 2026, 4:09 p.m. |
| PDg | Predicate description generation | batch_69bd73089f548190834103366e24ab40 |
completed | March 20, 2026, 4:17 p.m. |
Created at: March 20, 2026, 1:33 p.m.