Triple
T14145007
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alps four-thousanders |
E350521
|
entity |
| Predicate | hasMember |
P10
|
FINISHED |
| Object | Pic Lory |
E491687
|
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: Pic Lory | Statement: [Alps four-thousanders, hasMember, Pic Lory]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pic Lory Context triple: [Alps four-thousanders, hasMember, Pic Lory]
-
A.
Pic Lory
chosen
Pic Lory is a prominent alpine summit in the French Alps, located in the Isère department and known for its challenging mountaineering routes and panoramic views.
-
B.
Monte Pearce
Monte Pearce is the son of Australian actor Guy Pearce and Dutch actress Carice van Houten.
-
C.
Pierre Loti Hill
Pierre Loti Hill is a scenic hilltop in Istanbul famed for its panoramic views over the Golden Horn and its historic café named after the French writer Pierre Loti.
-
D.
Roque
Roque is a French surname notably borne by Jacqueline Roque, the second wife of Pablo Picasso.
-
E.
Roque
Roque is a key member of the black-ops team in the action film "The Losers," known for his tough, pragmatic nature and complex loyalties.
- 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_69d827865f608190b311820428ae027b |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de61214de081909a5186ff11336f97 |
completed | April 14, 2026, 3:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcdf1b8508819096d4f5cf1456edca |
completed | May 7, 2026, 6:51 p.m. |
Created at: April 10, 2026, 12:53 a.m.