Triple
T37845580
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Siege of Fort St. Philip |
E943589
|
entity |
| Predicate | locationFort |
P133132
|
FINISHED |
| Object | Castillo de San Felipe |
E552632
|
NE 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: Castillo de San Felipe | Statement: [Siege of Fort St. Philip, locationFort, Castillo de San Felipe]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locationFort Context triple: [Siege of Fort St. Philip, locationFort, Castillo de San Felipe]
-
A.
fortressLocation
chosen
Indicates that a fortress is located at or in a specified place or geographic area.
-
B.
locationFound
Indicates that a particular entity is located or discovered at a specific place or position.
-
C.
locationFormed
Indicates the place or geographic area where an entity (such as an organization, group, or structure) was originally established or came into existence.
-
D.
locationScrapped
Indicates that the location associated with an entity has been removed, discarded, or is no longer considered valid or in use.
-
E.
locationOfFacility
Indicates that a facility is situated at or associated with a specific geographic location.
- F. None of above.
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_69f76eeb0f7081908d6d3adbc469889c |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a037c903be48190a2fafa53d7d50d42 |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a41041a31588190bee707f4e58c6c04 |
completed | June 28, 2026, 11:23 a.m. |
| PD | Predicate disambiguation | batch_6a037a192a008190a9917688a9e804f4 |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:19 p.m.