Triple
T22421830
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mitsubishi Hitachi Tool Engineering |
E554265
|
entity |
| Predicate | materialMachined |
P148107
|
FINISHED |
| Object | steel |
—
|
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: steel | Statement: [Mitsubishi Hitachi Tool Engineering, materialMachined, steel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: materialMachined Context triple: [Mitsubishi Hitachi Tool Engineering, materialMachined, steel]
-
A.
materialUsed
Indicates that one entity is made from, incorporates, or utilizes the other entity as its material or substance.
-
B.
material
Indicates that one entity is physically composed of, made from, or constructed using the substance or material represented by the other entity.
-
C.
materialFormedIn
Indicates that a material is created, produced, or formed within a specified process, environment, or context.
-
D.
materialOptions
Indicates that there are one or more possible materials that can be chosen or applied in relation to a given entity or context.
-
E.
materialSpecialization
Indicates a relationship where one material is a specialized, more specific, or refined form of another more general material.
- 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_69e11e4f2d0c819091aa3558ea2ee630 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1594b08d88190bb61a30397d0ffa5 |
completed | April 29, 2026, 1:05 a.m. |
| PD | Predicate disambiguation | batch_69e8989495bc81909d2699fce5992e28 |
completed | April 22, 2026, 9:44 a.m. |
| PDg | Predicate description generation | batch_69e8aa39e3388190b659d59948ebf3e6 |
completed | April 22, 2026, 11 a.m. |
Created at: April 16, 2026, 8:46 p.m.