Triple
T21080234
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tollund Man |
E519343
|
entity |
| Predicate | scientificAnalysis |
P104001
|
FINISHED |
| Object | radiocarbon dating |
—
|
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: radiocarbon dating | Statement: [Tollund Man, scientificAnalysis, radiocarbon dating]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scientificAnalysis Context triple: [Tollund Man, scientificAnalysis, radiocarbon dating]
-
A.
analyzes
Indicates that one entity systematically examines or evaluates another entity to understand its nature, structure, or components.
-
B.
analysisType
chosen
Indicates the specific kind or category of analysis being applied or performed in relation to an entity or dataset.
-
C.
scientificResearch
Indicates that an entity conducts, participates in, or is the subject of systematic scientific investigation or study.
-
D.
hasAnalysis
Indicates that an entity is associated with, or has undergone, a particular analysis or examination.
-
E.
helpsAnalyze
Indicates that one entity assists another in examining, interpreting, or understanding something in a more detailed or effective way.
- 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_69e0b506e59c8190849b71ed07929215 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e702da7be881908e430518103d7bb1 |
completed | April 21, 2026, 4:53 a.m. |
| PD | Predicate disambiguation | batch_69e5dbfcd5e881908f1e4e0d2d237856 |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 16, 2026, 2:49 p.m.