Triple

T25979642

Position	Surface form	Disambiguated ID	Type / Status
Subject	four-momentum operator	`E646031`	entity
Predicate	frameTransformsAs	`P28224`	FINISHED
Object	Lorentz four-vector A Lorentz four-vector is a mathematical object in special relativity that combines time and three-dimensional space components into a single entity transforming linearly under Lorentz transformations.	`E1703111`	NE FINISHED

How this triple was built (3 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: Lorentz four-vector | Statement: [four-momentum operator, frameTransformsAs, Lorentz four-vector]

NEDg Description generation gpt-5.1

Instruction

Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"

Input

Entity: Lorentz four-vector
Triple: [four-momentum operator, frameTransformsAs, Lorentz four-vector]

Generated description

A Lorentz four-vector is a mathematical object in special relativity that combines time and three-dimensional space components into a single entity transforming linearly under Lorentz transformations.

PD Predicate disambiguation gpt-5-mini-2025-08-07

Target predicate: frameTransformsAs
Context triple: [four-momentum operator, frameTransformsAs, Lorentz four-vector]

A. framesAs
Indicates how one entity presents, characterizes, or interprets another entity or situation in a particular light or context.
B. transformsUnder chosen
Indicates a relationship where one entity changes form, state, or structure when subjected to the influence, conditions, or operation specified by another entity.
C. framesViewOf
Indicates that one entity provides a framing, perspective, or interpretive context through which another entity is viewed or understood.
D. coordinateTransformation
Indicates a relationship where one coordinate system is mathematically converted or mapped into another, preserving the correspondence of points between them.
E. regionTransformed
Indicates that one region has been changed or converted into another region through some transformation process.
F. None of above.

Provenance (6 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_69e77e881fc08190ba1c8dc7e2a07f97`	completed	April 21, 2026, 1:41 p.m.
NER	Named-entity recognition	`batch_69f6050e507881909e3bc0c33e8a8c7e`	completed	May 2, 2026, 2:07 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a11078dd2dc8190b4b36697dfd4680b`	completed	May 23, 2026, 1:49 a.m.
NEDg	Description generation	`batch_6a11085043a08190b86f770075f609c1`	completed	May 23, 2026, 1:52 a.m.
NED2	Entity disambiguation (via description)	`batch_6a110925bec881908c0bdb63355e4e31`	completed	May 23, 2026, 1:55 a.m.
PD	Predicate disambiguation	`batch_69f5f7fba5248190945acf1561280799`	completed	May 2, 2026, 1:11 p.m.

Created at: April 22, 2026, 8:54 a.m.