Triple
T15898292
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Steel |
E385520
|
entity |
| Predicate | hasTypicalCarbonContentRange |
P120970
|
FINISHED |
| Object | 0.02–2.1% by weight |
—
|
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: 0.02–2.1% by weight | Statement: [Steel, hasTypicalCarbonContentRange, 0.02–2.1% by weight]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTypicalCarbonContentRange Context triple: [Steel, hasTypicalCarbonContentRange, 0.02–2.1% by weight]
-
A.
carbonateContent
Indicates the proportion or amount of carbonate present in a given material or sample.
-
B.
hasFuelEnrichmentRange
Indicates that there is a specified range of fuel enrichment levels associated with an entity or relationship.
-
C.
hasAverageCompositionByVolume
Indicates that one entity has another entity as its specified average proportion of total volume in a mixture or system.
-
D.
hasPrimaryCarbohydrate
Indicates that one entity has another entity as its main or principal carbohydrate component.
-
E.
containsNaturallyOccurringElements
Indicates that something includes elements that occur in nature without human alteration or synthesis.
- 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_69d86da5b800819083a31be937d738b0 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e17d4d08f481909f38b75e3f42d9ab |
completed | April 17, 2026, 12:22 a.m. |
| PD | Predicate disambiguation | batch_69e142ca3b208190946c3aa4c1e6087c |
completed | April 16, 2026, 8:12 p.m. |
| PDg | Predicate description generation | batch_69e17d48cc9c8190b03fd07ae2e9dfd8 |
completed | April 17, 2026, 12:22 a.m. |
Created at: April 10, 2026, 4:51 a.m.