Triple
T1003711
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Abu Sir necropolis |
E21660
|
entity |
| Predicate | hasEarliestEvidence |
P3921
|
FINISHED |
| Object | Early Dynastic Period burials |
—
|
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: Early Dynastic Period burials | Statement: [Abu Sir necropolis, hasEarliestEvidence, Early Dynastic Period burials]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEarliestEvidence Context triple: [Abu Sir necropolis, hasEarliestEvidence, Early Dynastic Period burials]
-
A.
earliestKnownAncestor
Indicates that one entity is the most distant (oldest) known ancestor in the lineage of another entity.
-
B.
archaeologicalEvidenceAge
Indicates the age or time period to which a piece of archaeological evidence is dated.
-
C.
firstClearlyAttestedIn
chosen
Indicates the earliest known point in time or source where something is clearly documented or evidenced.
-
D.
locationOfEarlyUse
Indicates the place where something was first or among the earliest instances to be used or applied.
-
E.
hasLanguageEvidenceOf
Indicates that there is linguistic or textual evidence supporting, documenting, or attesting to the related entity or claim.
- 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_69a493c53e648190ae8cb76c433fd9a7 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b4ff614081909478500ada1f5059 |
completed | March 1, 2026, 9:51 p.m. |
| PD | Predicate disambiguation | batch_69a4b2b1f4f88190822598cfd2a0fd2b |
completed | March 1, 2026, 9:42 p.m. |
Created at: March 1, 2026, 7:41 p.m.