Triple
T115433
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aden (until 1937, administratively linked) |
E2327
|
entity |
| Predicate | hasLegalChange |
P6150
|
FINISHED |
| Object | separated from British India in 1937 |
—
|
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: separated from British India in 1937 | Statement: [Aden (until 1937, administratively linked), hasLegalChange, separated from British India in 1937]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLegalChange Context triple: [Aden (until 1937, administratively linked), hasLegalChange, separated from British India in 1937]
-
A.
hasLegalStatus
Indicates that an entity possesses a particular legal classification, recognition, or standing under law.
-
B.
hasLegalIssue
Indicates that an entity is involved in, associated with, or subject to a legal problem, dispute, or proceeding.
-
C.
hasLegalEffectToday
Indicates that a legal rule, document, or status is currently in force and produces legal consequences as of today.
-
D.
hasLegalProceeding
Indicates that there is a formal legal action, case, or proceeding involving the related entities.
-
E.
usesLegalCode
Indicates that one entity applies, references, or operates under a particular legal code in its actions or regulations.
- 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_69a2506c5428819085c28a8884790e29 |
completed | Feb. 28, 2026, 2:18 a.m. |
| NER | Named-entity recognition | batch_69a257845c548190bfb49409988d1c57 |
completed | Feb. 28, 2026, 2:48 a.m. |
| PD | Predicate disambiguation | batch_69a256456d908190b52c937fe6c4343f |
completed | Feb. 28, 2026, 2:43 a.m. |
| PDg | Predicate description generation | batch_69a2578329d08190be82e004b8224d2b |
completed | Feb. 28, 2026, 2:48 a.m. |
Created at: Feb. 28, 2026, 2:24 a.m.