Triple
T13987078
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Seven Seas |
E336467
|
entity |
| Predicate | mentionedSince |
P112060
|
FINISHED |
| Object | antiquity |
—
|
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: antiquity | Statement: [Seven Seas, mentionedSince, antiquity]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mentionedSince Context triple: [Seven Seas, mentionedSince, antiquity]
-
A.
mentionedWith
Indicates that two entities are mentioned together or in close association within the same context, such as a document, sentence, or conversation.
-
B.
coveredSince
Indicates that one entity has been under the protection, applicability, or effect of another entity continuously starting from a specified point in time.
-
C.
mentionedAs
Indicates that one entity is referred to or cited by name or description in the context of another entity.
-
D.
knownSince
Indicates the point in time from which one entity has been aware of, acquainted with, or in possession of knowledge about another entity.
-
E.
mentions
Indicates that one entity refers to, cites, or brings up another entity in some form of communication or content.
- 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_69d81c639e808190a0e4b4f3d31c6a59 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2ea537408190bb9d35963886803f |
completed | April 14, 2026, 12:10 p.m. |
| PD | Predicate disambiguation | batch_69dd465dfbc4819090d8c61fd572d35f |
completed | April 13, 2026, 7:39 p.m. |
| PDg | Predicate description generation | batch_69de01ed2098819088ec45069f6f2609 |
completed | April 14, 2026, 8:59 a.m. |
Created at: April 9, 2026, 10:18 p.m.