Triple
T15898353
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Steel |
E385520
|
entity |
| Predicate | hasTypicalMeltingPointRange |
P19716
|
FINISHED |
| Object | Approximately 1370–1510 °C |
—
|
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: Approximately 1370–1510 °C | Statement: [Steel, hasTypicalMeltingPointRange, Approximately 1370–1510 °C]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTypicalMeltingPointRange Context triple: [Steel, hasTypicalMeltingPointRange, Approximately 1370–1510 °C]
-
A.
meltingPoint
chosen
Indicates the temperature at which a substance changes from solid to liquid under specified conditions.
-
B.
hasTypicalFreezingPoint
Indicates the temperature at which a substance normally changes from liquid to solid under standard conditions.
-
C.
canMelt
Indicates that one entity has the capability to melt another entity or substance under appropriate conditions.
-
D.
boilingPoint
Indicates the temperature at which a substance changes from liquid to gas under specified pressure conditions.
-
E.
hasMeltingMechanism
Indicates that an entity possesses a specific mechanism or process by which it melts or causes melting.
- 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_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. |
Created at: April 10, 2026, 4:51 a.m.