Triple
T209947
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Primitive Irish |
E4691
|
entity |
| Predicate | hasWritingMedium |
P7961
|
FINISHED |
| Object | stone monuments |
—
|
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: stone monuments | Statement: [Primitive Irish, hasWritingMedium, stone monuments]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWritingMedium Context triple: [Primitive Irish, hasWritingMedium, stone monuments]
-
A.
hasAssociatedMedium
chosen
Indicates that one entity is linked to another entity that serves as its medium, format, or channel of expression or transmission.
-
B.
usedMedium
Indicates that an action or communication was carried out through a particular medium or channel.
-
C.
hasPublishingFormat
Indicates that an entity is associated with a specific format or medium in which it is published or made publicly available.
-
D.
hasWritingHistory
Indicates that an entity has a recorded history or log of its writing-related actions, changes, or authored content over time.
-
E.
hasLiteraryForm
Indicates that one entity is expressed, structured, or realized in a particular literary form (such as a genre, style, or textual format).
- 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_69a2575cb1dc8190a01ad332426dc339 |
completed | Feb. 28, 2026, 2:47 a.m. |
| NER | Named-entity recognition | batch_69a25d35aa288190966b6e15af1525cb |
completed | Feb. 28, 2026, 3:12 a.m. |
| PD | Predicate disambiguation | batch_69a25b4f71b88190866c8262922ae204 |
completed | Feb. 28, 2026, 3:04 a.m. |
Created at: Feb. 28, 2026, 2:52 a.m.