Triple
T25758763
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Titti |
E648675
|
entity |
| Predicate | preRomanPeopleOf |
P76180
|
FINISHED |
| Object | Iberia |
—
|
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: Iberia | Statement: [Titti, preRomanPeopleOf, Iberia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: preRomanPeopleOf Context triple: [Titti, preRomanPeopleOf, Iberia]
-
A.
preRomanPolity
Indicates that an entity functioned as a political or governmental unit that existed before the establishment or dominance of Roman rule in a given region.
-
B.
preRomanLanguage
Indicates that a language existed or was used in a region before the arrival or dominance of Roman rule or the Latin language.
-
C.
preRomanPopulation
chosen
Indicates that the subject represents the population that existed in a place before the arrival or dominance of Roman civilization.
-
D.
preRomanRegion
Indicates that a region existed or was defined in the period before Roman rule or influence.
-
E.
preRomanName
Indicates the name by which an entity (such as a place or people) was known before the Roman period or prior to receiving a Roman-era name.
- 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_69e7ab314d788190b3abe19e114080e1 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f5fd847ee48190a32b6b618d66f22d |
completed | May 2, 2026, 1:35 p.m. |
| PD | Predicate disambiguation | batch_69f4938262ac8190b41f922d0407d272 |
completed | May 1, 2026, 11:50 a.m. |
Created at: April 22, 2026, 4:43 a.m.