Triple
T38086431
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anping Fort |
E950986
|
entity |
| Predicate | functionIn17thCentury |
P180684
|
FINISHED |
| Object | key colonial stronghold |
—
|
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: key colonial stronghold | Statement: [Anping Fort, functionIn17thCentury, key colonial stronghold]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: functionIn17thCentury Context triple: [Anping Fort, functionIn17thCentury, key colonial stronghold]
-
A.
functionDuring17thCentury
chosen
Indicates that an entity performed its function or was active during the 17th century.
-
B.
functionDuring16thCentury
Indicates that an entity performed its function or was in operation specifically during the 16th century.
-
C.
historicalFormulationCentury
Indicates the century during which something was originally formulated or first established.
-
D.
functionDuringAncienRegime
Indicates that an entity held or performed a particular official role, duty, or function specifically during the Ancien Régime period.
-
E.
countryDuring17thCentury
Indicates that an entity functioned as a country during some or all of the 17th century.
- 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_69f76f03a3608190a73fd6df87c792a8 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fc4748843c8190931432653be4890c |
completed | May 7, 2026, 8:03 a.m. |
| PD | Predicate disambiguation | batch_69fc45646ce481908caf292ff9f06e15 |
completed | May 7, 2026, 7:55 a.m. |
Created at: May 3, 2026, 4:21 p.m.