Triple
T7347262
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | colossal statue of Ramesses II |
E169409
|
entity |
| Predicate | portraysTitle |
P30784
|
FINISHED |
| Object | King of Upper and Lower Egypt |
—
|
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: King of Upper and Lower Egypt | Statement: [colossal statue of Ramesses II, portraysTitle, King of Upper and Lower Egypt]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: portraysTitle Context triple: [colossal statue of Ramesses II, portraysTitle, King of Upper and Lower Egypt]
-
A.
portraysActorAs
Indicates that one entity depicts or represents an actor in a particular role, character, or manner.
-
B.
portrayedVia
Indicates that one entity is represented, depicted, or expressed through a particular medium, method, or channel.
-
C.
scriptOfTitle
Indicates that a script (e.g., a written work or screenplay) is associated with or belongs to a particular titled work.
-
D.
titleRepresents
chosen
Indicates that a given title stands for, denotes, or symbolizes a particular concept, role, work, or entity.
-
E.
títuloCompleto
Indicates that one entity is the full or complete title (including all its components or formal wording) associated with 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_69c68a5878888190968ce4d04db8d69f |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f139505c8190a7158cf59a6e089e |
completed | March 27, 2026, 9:06 p.m. |
| PD | Predicate disambiguation | batch_69c6f02aeeb8819099d1626566cec18b |
completed | March 27, 2026, 9:01 p.m. |
Created at: March 27, 2026, 3:05 p.m.