Triple
T11047314
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harad |
E261165
|
entity |
| Predicate | knownFor |
P22
|
FINISHED |
| Object | mûmakil |
E732686
|
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: mûmakil | Statement: [Harad, knownFor, mûmakil]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: mûmakil Context triple: [Harad, knownFor, mûmakil]
-
A.
Mûmakil
chosen
The Mûmakil are gigantic, elephant-like war beasts from J.R.R. Tolkien’s Middle-earth, most famously used as living siege engines by the forces of Sauron.
-
B.
mun
The mun was the traditional Korean coin-based currency used during the Joseon dynasty before the adoption of modern monetary systems.
-
C.
Mulukhiyah
Mulukhiyah is a traditional Middle Eastern and North African dish made from finely chopped jute leaves, typically cooked into a garlicky, spiced green stew often served with rice or bread.
-
D.
mun2
mun2 was a U.S. Spanish-language cable television network targeting young Latino audiences, later rebranded as NBC Universo.
-
E.
MUHBA
MUHBA is Barcelona’s city history museum, dedicated to preserving and showcasing the urban, archaeological, and cultural heritage of Barcelona.
- 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_69d6aa98650481908609c7c56bfa7902 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d798315b988190bc565581b2664009 |
completed | April 9, 2026, 12:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e3a9fad8248190810e097d148655f5 |
completed | April 18, 2026, 3:57 p.m. |
Created at: April 8, 2026, 9:26 p.m.