Triple
T31840598
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ram in a Thicket |
E812790
|
entity |
| Predicate | foundInGraveComplex |
P137092
|
FINISHED |
| Object | Royal Cemetery at Ur |
—
|
NE NERFINISHED |
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: Royal Cemetery at Ur | Statement: [Ram in a Thicket, foundInGraveComplex, Royal Cemetery at Ur]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: foundInGraveComplex Context triple: [Ram in a Thicket, foundInGraveComplex, Royal Cemetery at Ur]
-
A.
burialComplexOf
Indicates that one entity is the burial complex associated with, containing, or dedicated to another entity (typically the person or group interred there).
-
B.
foundInTomb
chosen
Indicates that an object or entity was discovered within a specific tomb or burial site.
-
C.
hasPartInGrave
Indicates that an entity includes another entity as a physical component or element within a grave.
-
D.
cemeteryComplex
Indicates a relationship where a site or structure functions as, or is part of, a cemetery complex used for burials or memorials.
-
E.
formerGraveOf
Indicates that a location once served as the grave of an entity, but no longer does (e.g., the remains have been moved or the grave has been removed).
- 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_69f348ea7ffc8190a2ab43d80277cf59 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69fde49a084081909d99b1e0258169d5 |
completed | May 8, 2026, 1:26 p.m. |
| PD | Predicate disambiguation | batch_69fde1d04bd881909a46ecbbf18dfe59 |
completed | May 8, 2026, 1:14 p.m. |
Created at: April 30, 2026, 11:49 p.m.