Triple
T31077838
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | vicus Portae Quirinalis |
E792016
|
entity |
| Predicate | likelyLedTo |
P18658
|
FINISHED |
| Object | Quirinal Gate of Rome |
—
|
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: Quirinal Gate of Rome | Statement: [vicus Portae Quirinalis, likelyLedTo, Quirinal Gate of Rome]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: likelyLedTo Context triple: [vicus Portae Quirinalis, likelyLedTo, Quirinal Gate of Rome]
-
A.
canLeadTo
chosen
Indicates that one entity, condition, or event has the potential to cause, result in, or bring about another.
-
B.
likelySource
Indicates that one entity is considered the probable origin or cause of another entity or event.
-
C.
likelyBehavior
Indicates the behavior or action that an entity is expected or predicted to exhibit under given circumstances.
-
D.
almostCaused
Indicates that one entity’s actions or state came close to causing an effect or event involving another entity, but the outcome ultimately did not occur.
-
E.
likelyUse
Indicates that one entity is expected or probable to use, employ, or make use of another entity in a given context.
- 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_69f224ccdbbc81909b0cdb4cc2d70c7a |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6a916d2e08190bafc01cba73b6469 |
completed | May 3, 2026, 1:47 a.m. |
| PD | Predicate disambiguation | batch_69f6a7548eb48190a69b60a3c6ad53b9 |
completed | May 3, 2026, 1:39 a.m. |
Created at: April 29, 2026, 9:02 p.m.