Triple
T21080217
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tollund Man |
E519343
|
entity |
| Predicate | stomachContents |
P142755
|
FINISHED |
| Object | porridge of grains and seeds |
—
|
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: porridge of grains and seeds | Statement: [Tollund Man, stomachContents, porridge of grains and seeds]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stomachContents Context triple: [Tollund Man, stomachContents, porridge of grains and seeds]
-
A.
stomachType
Indicates the kind or classification of stomach an entity has, typically describing its structural or functional type.
-
B.
digestiveSystem
Indicates the relationship in which an entity possesses or is associated with a system responsible for breaking down food and absorbing nutrients.
-
C.
hasStomachType
Indicates that an entity possesses or is characterized by a specific type or classification of stomach.
-
D.
isEatenIn
Indicates that one entity (typically food) is consumed within the context, location, or occasion specified by another entity.
-
E.
largelyConsumedBy
Indicates that something is mostly or predominantly eaten or used up by a particular consumer or group.
- F. None of above. chosen
Provenance (4 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. |
| PDg | Predicate description generation | batch_69e5e2e03d88819086f8b641656ad8b0 |
completed | April 20, 2026, 8:25 a.m. |
Created at: April 16, 2026, 2:49 p.m.