Triple
T7569808
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ancient ruins of Hippo Regius |
E179209
|
entity |
| Predicate | hasRemainsFromEra |
P16216
|
FINISHED |
| Object | Punic era |
—
|
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: Punic era | Statement: [ancient ruins of Hippo Regius, hasRemainsFromEra, Punic era]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRemainsFromEra Context triple: [ancient ruins of Hippo Regius, hasRemainsFromEra, Punic era]
-
A.
hasEraReset
Indicates that a new era or time period has been initiated, resetting the previous temporal sequence or counting.
-
B.
endedEra
Indicates that one entity brought about or marked the conclusion of a particular era associated with another entity.
-
C.
hasRemainsOf
chosen
Indicates that one entity physically contains, preserves, or is associated with the leftover physical traces or remnants of another entity.
-
D.
preservesEra
Indicates that something maintains or keeps intact the characteristics, style, or conditions of a particular historical period.
-
E.
appliesToEra
Indicates that something is relevant, valid, or in effect during a particular historical or temporal era.
- 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_69c69f316e50819081a271c85c06f918 |
completed | March 27, 2026, 3:16 p.m. |
| NER | Named-entity recognition | batch_69c6f91ec780819099de6227a27bf5a5 |
completed | March 27, 2026, 9:39 p.m. |
| PD | Predicate disambiguation | batch_69c6f4de77048190b8769e717fdcf8e7 |
completed | March 27, 2026, 9:21 p.m. |
Created at: March 27, 2026, 3:51 p.m.