Triple
T38403353
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman theatre of Mérida |
E900957
|
entity |
| Predicate | originalCityFunction |
P204640
|
FINISHED |
| Object | capital of Lusitania |
—
|
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: capital of Lusitania | Statement: [Roman theatre of Mérida, originalCityFunction, capital of Lusitania]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalCityFunction Context triple: [Roman theatre of Mérida, originalCityFunction, capital of Lusitania]
-
A.
cityOfOriginal
Indicates the city from which something or someone originally comes or was first created or established.
-
B.
primaryCityFunction
Indicates the main role or purpose that a city serves within its broader region or system (e.g., political, economic, cultural center).
-
C.
nativeCity
Indicates that a city is the place where a person was born or is originally from.
-
D.
cityFunction
Indicates the primary role, purpose, or functional classification associated with a city (e.g., administrative, commercial, industrial, cultural).
-
E.
homeCityInBackstory
Indicates that an entity has a specified city as its home city within its narrative or character backstory.
- F. None of above. chosen
Provenance (4 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_69f76e6071a081909eea7a670d21420c |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037cae084081909004d77514c5f286 |
completed | May 12, 2026, 7:17 p.m. |
| PD | Predicate disambiguation | batch_6a037a1c850c819088795a7ae59bdeb8 |
completed | May 12, 2026, 7:06 p.m. |
| PDg | Predicate description generation | batch_6a037c84ecbc81908232e5215355f43b |
completed | May 12, 2026, 7:16 p.m. |
Created at: May 3, 2026, 4:31 p.m.