Triple
T1810472
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Berytus |
E40318
|
entity |
| Predicate | archaeologicalRemainsFoundIn |
P18735
|
FINISHED |
| Object | downtown Beirut |
—
|
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: downtown Beirut | Statement: [Berytus, archaeologicalRemainsFoundIn, downtown Beirut]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: archaeologicalRemainsFoundIn Context triple: [Berytus, archaeologicalRemainsFoundIn, downtown Beirut]
-
A.
archaeologicalFindsInclude
Indicates that the set of archaeological finds at a site or context contains or encompasses the specified items or types of artifacts.
-
B.
excavationSite
Indicates a location where digging or removal of earth or materials is actively conducted, typically for construction, mining, or archaeological purposes.
-
C.
notableArchaeologicalSite
chosen
Indicates that a place is recognized as an archaeologically significant site, typically due to important historical remains, artifacts, or research findings.
-
D.
excavatedAt
Indicates that an excavation activity took place at a specific location or site.
-
E.
hasArchaeologicalSiteType
Indicates that an entity is classified as, or associated with, a specific type or category of archaeological site.
- 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_69a88643a3388190a612f2ebe1fb29e7 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69ab694d75ac8190a4d61399c04b9fb9 |
completed | March 6, 2026, 11:54 p.m. |
| PD | Predicate disambiguation | batch_69aa61d6b8ec8190a1597b2e44ea6534 |
completed | March 6, 2026, 5:10 a.m. |
Created at: March 4, 2026, 7:32 p.m.