Triple
T19473050
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hilti Corporation |
E487172
|
entity |
| Predicate | headquartersLocation |
P62
|
FINISHED |
| Object | Schaan, Liechtenstein |
—
|
NE NERFINISHED |
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: Schaan, Liechtenstein | Statement: [Hilti Corporation, headquartersLocation, Schaan, Liechtenstein]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Schaan, Liechtenstein Context triple: [Hilti Corporation, headquartersLocation, Schaan, Liechtenstein]
-
A.
Schaan
chosen
Schaan is a major municipality in Liechtenstein known as its principal urban and industrial center.
-
B.
Vaduz
Vaduz is the small alpine town that serves as the political and cultural center of the Principality of Liechtenstein.
-
C.
Balzers
Balzers is a municipality in southern Liechtenstein known for its scenic Alpine setting and historic Gutenberg Castle.
-
D.
Ruggell
Ruggell is a northern Liechtenstein municipality known for its flat Rhine valley landscape and agricultural character.
-
E.
Liestal
Liestal is a historic Swiss town in northwestern Switzerland that serves as the administrative and cultural center of the canton of Basel-Landschaft.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e8d924388190b847cb15bb3d0aff |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e633ea604c8190a2feacb709b7ca27 |
completed | April 20, 2026, 2:10 p.m. |
Created at: April 10, 2026, 1:39 p.m.