Triple
T110418
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | open-hearth process |
E2235
|
entity |
| Predicate | usesRefractoryLining |
P1272
|
FINISHED |
| Object | acid lining |
—
|
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: acid lining | Statement: [open-hearth process, usesRefractoryLining, acid lining]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesRefractoryLining Context triple: [open-hearth process, usesRefractoryLining, acid lining]
-
A.
mantlingLined
Indicates that the inner surface of a heraldic mantling is lined with a specified material, color, or pattern.
-
B.
materialUsed
chosen
Indicates that one entity is made from, incorporates, or utilizes the other entity as its material or substance.
-
C.
usedInProductLine
Indicates that something (such as a component, material, or feature) is utilized within a particular product line.
-
D.
hasMezzanine
Indicates that one entity includes or is equipped with a mezzanine level in relation to another entity.
-
E.
drainageType
Indicates the kind or classification of drainage associated with or applied to an entity (e.g., how water is removed or flows from it).
- 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_69a24fcdaeb48190a2d796677e4b3281 |
completed | Feb. 28, 2026, 2:15 a.m. |
| NER | Named-entity recognition | batch_69a258b58efc8190959c86f73d67b744 |
completed | Feb. 28, 2026, 2:53 a.m. |
| PD | Predicate disambiguation | batch_69a25641058c8190b5b64509b35d8176 |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:20 a.m.