Triple
T9567406
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fall of Corregidor |
E230821
|
entity |
| Predicate | hasFortifications |
P22477
|
FINISHED |
| Object | Fort Mills |
E74339
|
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: Fort Mills | Statement: [Fall of Corregidor, hasFortifications, Fort Mills]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fort Mills Context triple: [Fall of Corregidor, hasFortifications, Fort Mills]
-
A.
Fort Mills
chosen
Fort Mills is the former U.S. Army coastal defense fortification that occupied most of Corregidor Island in the Philippines and played a key role in World War II’s Pacific theater.
-
B.
Union Mills
Union Mills is a small village on the Isle of Man, situated just inland from the island’s capital, Douglas.
-
C.
Mauldin
Mauldin is the surname of American music producer, songwriter, and record executive Jermaine Dupri.
-
D.
Mauldin
Mauldin is a city in South Carolina, United States, known as a suburban community within the Greenville metropolitan area.
-
E.
High Point
High Point is a prominent summit in the Bull Run Mountains, known as one of the range’s higher elevations and a local hiking destination.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca847f22188190a56e4a97625bef22 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd996df4f08190b19bbaefb10a9789 |
completed | April 1, 2026, 10:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d152b09c808190aff32419f2cbb15f |
completed | April 4, 2026, 6:04 p.m. |
Created at: March 30, 2026, 8:04 p.m.