Triple
T16121964
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Citroën AX |
E391168
|
entity |
| Predicate | fuelEconomyHighlight |
P23422
|
FINISHED |
| Object | very low fuel consumption for its era |
—
|
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: very low fuel consumption for its era | Statement: [Citroën AX, fuelEconomyHighlight, very low fuel consumption for its era]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fuelEconomyHighlight Context triple: [Citroën AX, fuelEconomyHighlight, very low fuel consumption for its era]
-
A.
fuelEfficiency
Indicates how effectively an entity uses fuel to perform a given amount of work or travel a certain distance.
-
B.
associatedWithFuelEconomy
chosen
Indicates a relationship where something is connected or relevant to fuel economy, such as influencing, measuring, or describing fuel efficiency.
-
C.
fuelConsumption
Indicates the amount of fuel used by an entity (such as a vehicle or device) over a specified distance, time, or operation.
-
D.
oilUsage
Indicates the amount or pattern of oil consumed or utilized by an entity over a given context or period.
-
E.
typicalFuel
Indicates the kind of fuel that is normally or most commonly used by an entity (such as a device, vehicle, or system).
- 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_69d87f1bb0988190b490d273dbf3fd03 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e2020198908190b56900cbfc53f25c |
completed | April 17, 2026, 9:48 a.m. |
| PD | Predicate disambiguation | batch_69e1828518c48190a8ef3aaa46a1f639 |
completed | April 17, 2026, 12:44 a.m. |
Created at: April 10, 2026, 5 a.m.