Triple
T8925955
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ur-Nammu |
E212538
|
entity |
| Predicate | lawCodeFeature |
P25070
|
FINISHED |
| Object | primarily monetary fines instead of physical punishments |
—
|
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: primarily monetary fines instead of physical punishments | Statement: [Ur-Nammu, lawCodeFeature, primarily monetary fines instead of physical punishments]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lawCodeFeature Context triple: [Ur-Nammu, lawCodeFeature, primarily monetary fines instead of physical punishments]
-
A.
featuresLaw
Indicates that something includes, presents, or is characterized by a particular law or legal provision.
-
B.
legalSystemFeature
chosen
Indicates a characteristic, rule, or structural element that forms part of a particular legal system.
-
C.
lawCharacteristicInText
Indicates that a specific legal characteristic or feature is expressed, described, or referenced within a given text.
-
D.
legalCodeName
Indicates that one entity is the official legal code designation or name assigned to another entity within a legal or regulatory system.
-
E.
legalCodeScript
Indicates that a legal code is written or represented using a particular writing system or script.
- 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_69ca839481d48190b42b037e0d0f636c |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc66700fb48190874563e535f20437 |
completed | April 1, 2026, 12:27 a.m. |
| PD | Predicate disambiguation | batch_69cc5ed3286c8190a21de2ee11f2639f |
completed | March 31, 2026, 11:54 p.m. |
Created at: March 30, 2026, 6:57 p.m.