Triple
T4121194
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tarquinia |
E92615
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Marta River |
E488342
|
NE 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: Marta River | Statement: [Tarquinia, locatedNear, Marta River]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marta River Context triple: [Tarquinia, locatedNear, Marta River]
-
A.
Marta River
chosen
The Marta River is a watercourse in central Italy that drains Lake Bolsena and flows southwest toward the Tyrrhenian Sea.
-
B.
Pilcomayo River
The Pilcomayo River is a major South American river that flows from the Andes through Bolivia, Paraguay, and Argentina before joining the Paraná River.
-
C.
San Lorenzo River
The San Lorenzo River is a coastal river in central California that flows through the city of Santa Cruz into the Monterey Bay.
-
D.
Zamora River
The Zamora River is a significant waterway in southern Ecuador that flows through the Andean and Amazonian regions, supporting local ecosystems and communities.
-
E.
Magé River
The Magé River is a watercourse in the state of Rio de Janeiro, Brazil, that flows through the municipality of Magé before emptying into Guanabara Bay.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69aed9685f70819086932777aec8d959 |
completed | March 9, 2026, 2:30 p.m. |
| NER | Named-entity recognition | batch_69af0203b8c88190b08dd64800a37168 |
completed | March 9, 2026, 5:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf8bb93044819094d61035355c08f0 |
completed | March 22, 2026, 6:27 a.m. |
Created at: March 9, 2026, 3:41 p.m.