Triple
T34353544
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Merneferre Ay |
E881649
|
entity |
| Predicate | knownFromArtifactType |
P157618
|
FINISHED |
| Object | scarab seal impressions |
—
|
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: scarab seal impressions | Statement: [Merneferre Ay, knownFromArtifactType, scarab seal impressions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: knownFromArtifactType Context triple: [Merneferre Ay, knownFromArtifactType, scarab seal impressions]
-
A.
hasTypeOfArtifact
Indicates that one entity is classified as, or belongs to, a particular type or category of artifact in relation to another entity.
-
B.
producedArtifactType
Indicates the type or category of artifact that is created or generated as the result of a production process or activity.
-
C.
artifactTypeFound
chosen
Indicates that a specific type of artifact has been discovered or identified in association with a given context or location.
-
D.
relatedArtifactType
Indicates the specific kind of relationship or linkage that one artifact has to another artifact (e.g., predecessor, successor, reference, dependency).
-
E.
knownFrom
Indicates that one entity is aware of, has learned about, or recognizes another entity through a specified source, context, or medium.
- 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_69f349bd06008190904c2f86c42749e3 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f757898fe48190b124dc7301672623 |
completed | May 3, 2026, 2:11 p.m. |
| PD | Predicate disambiguation | batch_69f754c484348190948d2a04ff228fb1 |
completed | May 3, 2026, 1:59 p.m. |
Created at: May 1, 2026, 1:58 a.m.