Triple
T21667815
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | São Francisco Square |
E534766
|
entity |
| Predicate | heritageProtectionAuthority |
P63420
|
FINISHED |
| Object | IPHAN |
—
|
NE NERFINISHED |
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: IPHAN | Statement: [São Francisco Square, heritageProtectionAuthority, IPHAN]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: IPHAN Context triple: [São Francisco Square, heritageProtectionAuthority, IPHAN]
-
A.
IPHAN
chosen
IPHAN is Brazil’s federal agency responsible for preserving and protecting the nation’s cultural, historical, and artistic heritage.
-
B.
IPH
IPH is the IATA airport code for Sultan Azlan Shah Airport serving Ipoh in the state of Perak, Malaysia.
-
C.
IPHC
IPHC is the commonly used abbreviation for Japan’s Intellectual Property High Court, a specialized court that handles intellectual property disputes.
-
D.
Ihy
Ihy is an ancient Egyptian god associated with music, joy, and childhood, often depicted as a child playing the sistrum and linked closely to his mother Hathor.
-
E.
Iphofen
Iphofen is a historic wine-growing town in northern Bavaria, Germany, known for its well-preserved medieval architecture and surrounding vineyards.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c46898008190aa618a4af55bd1ee |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef6c0cf6208190a8bd9fa423c65a40 |
completed | April 27, 2026, 2 p.m. |
Created at: April 16, 2026, 6:37 p.m.