Triple
T29271927
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prince Kawab |
E742140
|
entity |
| Predicate | notableFeatureOfTomb |
P116515
|
FINISHED |
| Object | double mastaba design |
—
|
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: double mastaba design | Statement: [Prince Kawab, notableFeatureOfTomb, double mastaba design]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableFeatureOfTomb Context triple: [Prince Kawab, notableFeatureOfTomb, double mastaba design]
-
A.
tombNotableFeature
chosen
Indicates that a tomb is distinguished or recognized for a particular notable feature or characteristic.
-
B.
notableFeatureOn
Indicates that one entity is a prominent or distinguishing feature located on or part of another entity.
-
C.
tombStructure
Indicates that one entity is a structure that serves as the tomb or burial place associated with another entity.
-
D.
tombDecoration
Indicates that something serves as an ornamental or symbolic adornment associated with a tomb.
-
E.
hasMausoleum
Indicates that one entity possesses, contains, or is associated with a mausoleum dedicated to another 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_69f0912124d48190a046642b69407f4c |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_6a0332a08b48819094aaed6e04a36886 |
completed | May 12, 2026, 2:01 p.m. |
| PD | Predicate disambiguation | batch_6a0331998a688190b5d919697d4231ac |
completed | May 12, 2026, 1:56 p.m. |
Created at: April 28, 2026, 12:48 p.m.