Triple
T28561215
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zeng state |
E722547
|
entity |
| Predicate | primaryKnowledgeSource |
P2296
|
FINISHED |
| Object | archaeology |
—
|
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: archaeology | Statement: [Zeng state, primaryKnowledgeSource, archaeology]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryKnowledgeSource Context triple: [Zeng state, primaryKnowledgeSource, archaeology]
-
A.
knowledgeSource
Indicates that one entity serves as the origin, provider, or reference of information or understanding for another entity.
-
B.
primarySources
chosen
Indicates that one entity serves as an original, authoritative source of information or evidence for another entity.
-
C.
knowledgeSourceInUniverse
Indicates that a particular source or repository of knowledge exists or is valid within a specified universe or contextual domain.
-
D.
primarySourcesDiscussed
Indicates that the primary source materials are examined, analyzed, or discussed in relation to the subject.
-
E.
primarySourcePassage
Indicates that a passage serves as the main or original source of information or evidence for a given claim, statement, or data item.
- 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_69f01a5f69d08190ad5c0d2167078dec |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_6a00532815c881908f10d9594458b3d7 |
completed | May 10, 2026, 9:43 a.m. |
| PD | Predicate disambiguation | batch_6a0052b9f030819081b8105bdcaf6d8f |
completed | May 10, 2026, 9:41 a.m. |
Created at: April 28, 2026, 4:05 a.m.