Triple
T28474610
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Via Valeria |
E720527
|
entity |
| Predicate | startingGateOfRome |
P195224
|
FINISHED |
| Object | Porta Esquilina |
—
|
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: Porta Esquilina | Statement: [Via Valeria, startingGateOfRome, Porta Esquilina]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startingGateOfRome Context triple: [Via Valeria, startingGateOfRome, Porta Esquilina]
-
A.
hillOfRome
Indicates that one entity is a hill that is located in or associated with the city of Rome.
-
B.
mainRomanSanctuary
Indicates that one entity serves as the primary Roman religious sanctuary or temple associated with another entity.
-
C.
erectedInRomeAs
Indicates that something was constructed or set up in the city of Rome in the role or capacity specified by the related entity.
-
D.
interactionWithRome
Indicates a relationship in which an entity engages in some form of contact, exchange, or involvement with Rome.
-
E.
oneOfLargestRomanAmphitheatres
Indicates that the subject is among the largest Roman amphitheatres in terms of size or capacity.
- 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_69f01a5983f48190b7c1b8857245a4f7 |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69fdb31800508190beec15adb9bbd292 |
completed | May 8, 2026, 9:55 a.m. |
| PD | Predicate disambiguation | batch_69fdb19c381c8190bafb2f565da097f1 |
completed | May 8, 2026, 9:49 a.m. |
| PDg | Predicate description generation | batch_69fdb3172b808190b590d7c5be31ebb7 |
completed | May 8, 2026, 9:55 a.m. |
Created at: April 28, 2026, 2:51 a.m.