Triple
T7921479
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nernst–Lamp |
E183953
|
entity |
| Predicate | replacedCarbonFilamentLamps |
P49726
|
FINISHED |
| Object | in some applications |
—
|
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: in some applications | Statement: [Nernst–Lamp, replacedCarbonFilamentLamps, in some applications]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: replacedCarbonFilamentLamps Context triple: [Nernst–Lamp, replacedCarbonFilamentLamps, in some applications]
-
A.
typeOfLampsUsed
Indicates the specific kinds or categories of lamps that are utilized in a given context or system.
-
B.
replacedInProduct
chosen
Indicates that one component or element in a product has been substituted or superseded by another component or element within that product.
-
C.
partlyReplacedBy
Indicates that one entity has been superseded or substituted in part, but not entirely, by another entity.
-
D.
plannedReplacement
Indicates that one entity is intended or scheduled to be replaced by another entity in the future.
-
E.
hasNumberOfShamashLights
Indicates the relationship specifying how many Shamash (helper) lights are present or associated with an object or setting.
- 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_69ca828efbe48190bd48482650182e79 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3a9499cc8190b6bd81f4625c77ab |
completed | March 31, 2026, 3:08 a.m. |
| PD | Predicate disambiguation | batch_69cae9316e98819080be7bf1a6ff92f1 |
completed | March 30, 2026, 9:20 p.m. |
Created at: March 30, 2026, 5:06 p.m.