Triple
T32662770
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ponte delle Torri |
E835063
|
entity |
| Predicate | possibleEarlierStructure |
P159860
|
FINISHED |
| Object | Roman aqueduct |
—
|
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: Roman aqueduct | Statement: [Ponte delle Torri, possibleEarlierStructure, Roman aqueduct]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: possibleEarlierStructure Context triple: [Ponte delle Torri, possibleEarlierStructure, Roman aqueduct]
-
A.
previousStructure
Indicates that one structure directly precedes another in a defined sequence or configuration.
-
B.
mayHaveStructure
Indicates that an entity is allowed or able to possess a particular internal organization, configuration, or structural form, though not necessarily required to do so.
-
C.
hasEarlierStructureOnSite
chosen
Indicates that a given site previously contained an earlier structure before the current one.
-
D.
usedStructure
Indicates that one entity makes use of, relies on, or operates through a particular structure (physical, logical, or organizational) to perform its function or action.
-
E.
possibleElement
Indicates that something can potentially be a member, component, or constituent part of another entity or set, without asserting that it actually is.
- 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_69f349303ccc8190a70d0f6e8a21d3fb |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f73223675481908c1bc3208c0f5284 |
completed | May 3, 2026, 11:31 a.m. |
| PD | Predicate disambiguation | batch_69f7317690108190b3aae2cd2e1d069e |
completed | May 3, 2026, 11:28 a.m. |
Created at: May 1, 2026, 1:08 a.m.