Triple
T13061143
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Piedras Negras |
E329197
|
entity |
| Predicate | hasNeighboringSite |
P108252
|
FINISHED |
| Object | La Mar |
E629250
|
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: La Mar | Statement: [Piedras Negras, hasNeighboringSite, La Mar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: La Mar Context triple: [Piedras Negras, hasNeighboringSite, La Mar]
-
A.
La Mar
chosen
La Mar is an archaeological site in the western Maya lowlands known for its Classic-period Maya ruins and inscriptions.
-
B.
L’Isula Rossa
L’Isula Rossa is the Corsican name for the coastal town and popular seaside resort of L’Île-Rousse in northern Corsica, France.
-
C.
The Seas
The Seas is an ocean-themed pavilion and aquarium attraction at EPCOT in Walt Disney World, featuring marine life exhibits and the Finding Nemo franchise.
-
D.
La Bahía
La Bahía was a key Spanish colonial presidio and settlement in what is now Texas, serving as an important military and mission outpost on the northern frontier of New Spain.
-
E.
The Sea
The Sea is a 1946 novel by French author Henri Bosco that explores themes of childhood, imagination, and the mysterious power of nature along the Mediterranean coast.
- 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_69d80771749c81909a6d9197b9504872 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d98bce3678819082a7aa1d83f20592 |
completed | April 10, 2026, 11:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6cbe45c8c819080fbdf1d94376feb |
completed | May 3, 2026, 4:15 a.m. |
Created at: April 9, 2026, 8:59 p.m.