Triple
T301660
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Old Town of Ghadamès |
E6208
|
entity |
| Predicate | builtWithMaterial |
P618
|
FINISHED |
| Object | mud brick |
—
|
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: mud brick | Statement: [Old Town of Ghadamès, builtWithMaterial, mud brick]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: builtWithMaterial Context triple: [Old Town of Ghadamès, builtWithMaterial, mud brick]
-
A.
materialUsed
Indicates that one entity is made from, incorporates, or utilizes the other entity as its material or substance.
-
B.
builtOn
Indicates that one entity is constructed, developed, or established using another entity as its base, foundation, or underlying platform.
-
C.
constructionType
Indicates the specific method or style by which something is built or constructed.
-
D.
builtProperty
Indicates that a constructed structure or building has been created on, or is associated with, a particular property or piece of land.
-
E.
material
chosen
Indicates that one entity is physically composed of, made from, or constructed using the substance or material represented by the other entity.
- 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_69a2e79230508190b912ecb555aae17e |
completed | Feb. 28, 2026, 1:03 p.m. |
| NER | Named-entity recognition | batch_69a2ea2fba548190a5aeb1597dca96bd |
completed | Feb. 28, 2026, 1:14 p.m. |
| PD | Predicate disambiguation | batch_69a2e93c367881908d3f6e2b81d44d7f |
completed | Feb. 28, 2026, 1:10 p.m. |
Created at: Feb. 28, 2026, 1:06 p.m.