Triple
T348776
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jerusalem |
E6995
|
entity |
| Predicate | earliestKnownReference |
P3921
|
FINISHED |
| Object | 2nd millennium BCE |
—
|
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: 2nd millennium BCE | Statement: [Jerusalem, earliestKnownReference, 2nd millennium BCE]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: earliestKnownReference Context triple: [Jerusalem, earliestKnownReference, 2nd millennium BCE]
-
A.
firstClearlyAttestedIn
chosen
Indicates the earliest known point in time or source where something is clearly documented or evidenced.
-
B.
historicalReference
Indicates that one entity refers to, cites, or alludes to another entity from an earlier time or historical context.
-
C.
earliestKnownAncestor
Indicates that one entity is the most distant (oldest) known ancestor in the lineage of another entity.
-
D.
languageOfEarliestForm
Indicates the language in which the earliest known form or attested version of something (e.g., a text, name, or expression) is recorded.
-
E.
discoveryDate
Indicates the date on which something was first discovered or identified.
- 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_69a2e7951ba08190960e90823b5078f3 |
completed | Feb. 28, 2026, 1:03 p.m. |
| NER | Named-entity recognition | batch_69a2eb1dc5f88190b54d084c6def7fc5 |
completed | Feb. 28, 2026, 1:18 p.m. |
| PD | Predicate disambiguation | batch_69a2e955d1f88190bd687c46fa7c5469 |
completed | Feb. 28, 2026, 1:10 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.