Triple
T1214510
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pompey’s Pillar |
E26077
|
entity |
| Predicate | survivingFrom |
P25058
|
FINISHED |
| Object | late Roman Alexandria |
—
|
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: late Roman Alexandria | Statement: [Pompey’s Pillar, survivingFrom, late Roman Alexandria]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: survivingFrom Context triple: [Pompey’s Pillar, survivingFrom, late Roman Alexandria]
-
A.
survivesAs
Indicates that one entity continues to exist or persist in place of, or after the end or transformation of, another entity.
-
B.
survivesIn
Indicates that an entity remains alive, functional, or intact within a specified environment, condition, or context.
-
C.
survivedEvent
Indicates that an entity continued to live or exist after experiencing and not being destroyed or killed by a particular event.
-
D.
survivingStructure
Indicates that a structure continues to exist or remain intact after a potentially destructive event or over a significant period of time.
-
E.
hasSurvivors
Indicates that one or more entities continue to exist or remain alive after a particular event, condition, or incident.
- 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_69a4948331fc8190b531ac9bec71c491 |
completed | March 1, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69a4be0370b4819093618930f4eecfcc |
completed | March 1, 2026, 10:30 p.m. |
| PD | Predicate disambiguation | batch_69a4bb62a7c08190a79dcb6ff72ac99b |
completed | March 1, 2026, 10:19 p.m. |
| PDg | Predicate description generation | batch_69a4bc6d5b7881908091e40c8695ef53 |
completed | March 1, 2026, 10:23 p.m. |
Created at: March 1, 2026, 7:46 p.m.