Triple

T31077838
Position Surface form Disambiguated ID Type / Status
Subject vicus Portae Quirinalis E792016 entity
Predicate likelyLedTo P18658 FINISHED
Object Quirinal Gate of Rome
The Quirinal Gate of Rome was an ancient city gate associated with the Quirinal Hill, serving as one of the northern entrances to the early Roman urban area.
 E1951859 NE FINISHED

How this triple was built (3 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]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Quirinal Gate of Rome
Triple: [vicus Portae Quirinalis, likelyLedTo, Quirinal Gate of Rome]
Generated description
The Quirinal Gate of Rome was an ancient city gate associated with the Quirinal Hill, serving as one of the northern entrances to the early Roman urban area.
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 (6 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.
NED1 Entity disambiguation (via context triple) batch_6a2958fc91488190a98b86c158e2ee54 completed June 10, 2026, 12:30 p.m.
NEDg Description generation batch_6a2959a8c0708190b8cf96f13be2bd37 completed June 10, 2026, 12:33 p.m.
NED2 Entity disambiguation (via description) batch_6a295d91f59c819096a9baa006e93830 completed June 10, 2026, 12:50 p.m.
PD Predicate disambiguation batch_69f6a7548eb48190a69b60a3c6ad53b9 completed May 3, 2026, 1:39 a.m.
Created at: April 29, 2026, 9:02 p.m.