Triple
T1219469
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman Amphitheatre of Alexandria |
E26184
|
entity |
| Predicate | discoveredDuring |
P3985
|
FINISHED |
| Object | construction works at Kom El-Dikka |
—
|
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: construction works at Kom El-Dikka | Statement: [Roman Amphitheatre of Alexandria, discoveredDuring, construction works at Kom El-Dikka]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: discoveredDuring Context triple: [Roman Amphitheatre of Alexandria, discoveredDuring, construction works at Kom El-Dikka]
-
A.
wasDiscoveredAt
chosen
Indicates that an entity was found, identified, or uncovered at a specific place or during a particular event or context.
-
B.
discoveredSince
Indicates that one entity has been discovered starting from, or at some point after, a specified time or event associated with another entity.
-
C.
discovery
Indicates the event or process by which one entity finds, uncovers, or identifies something previously unknown or unrecognized.
-
D.
discoveryDate
Indicates the date on which something was first discovered or identified.
-
E.
locatedAtTimeOfDiscovery
Indicates the place where something was situated at the moment it was first discovered.
- 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_69a4948331fc8190b531ac9bec71c491 |
completed | March 1, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69a4be1d55a08190a138b2411a7c4376 |
completed | March 1, 2026, 10:30 p.m. |
| PD | Predicate disambiguation | batch_69a4bb644af08190ba25905f20adb01a |
completed | March 1, 2026, 10:19 p.m. |
Created at: March 1, 2026, 7:46 p.m.