Triple
T36290593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Magna Steyr |
E893215
|
entity |
| Predicate | operatesAssemblyPlantIn |
P203557
|
FINISHED |
| Object | Graz |
E91728
|
NE 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: Graz | Statement: [Magna Steyr, operatesAssemblyPlantIn, Graz]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatesAssemblyPlantIn Context triple: [Magna Steyr, operatesAssemblyPlantIn, Graz]
-
A.
hasAssemblyLine
Indicates that one entity possesses or operates an assembly line used for producing or assembling items.
-
B.
steelPlantOperator
Indicates that one entity operates or manages a steel plant in relation to another entity.
-
C.
involvedInComplexAssembly
Indicates that an entity participates in the process of assembling or forming a larger molecular or structural complex.
-
D.
operatedPlantType
Indicates that an entity operates or manages a plant (facility) of a specified type.
-
E.
roleInAssembly
Indicates the specific function, position, or responsibility an entity holds within a particular assembly or gathering.
- F. None of above. chosen
Provenance (5 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_69f76e4955c08190b8cfddca34fc0242 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a01a23d8b148190ac2c8765aa9227c4 |
completed | May 11, 2026, 9:32 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3efd9cabb8819087f19b2bc1c125b7 |
completed | June 26, 2026, 10:30 p.m. |
| PD | Predicate disambiguation | batch_6a01a1e8bb90819096647e929bfb3db8 |
completed | May 11, 2026, 9:31 a.m. |
| PDg | Predicate description generation | batch_6a01a23ce3b08190acb03793824baf68 |
completed | May 11, 2026, 9:32 a.m. |
Created at: May 3, 2026, 4:09 p.m.