Triple
T8925902
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gilgamesh |
E212537
|
entity |
| Predicate | opponent |
P437
|
FINISHED |
| Object | Humbaba |
E233614
|
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: Humbaba | Statement: [Gilgamesh, opponent, Humbaba]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Humbaba Context triple: [Gilgamesh, opponent, Humbaba]
-
A.
Humbaba
chosen
Humbaba is the monstrous guardian of the Cedar Forest in the Mesopotamian Epic of Gilgamesh, known for his terrifying power and eventual defeat by Gilgamesh and Enkidu.
-
B.
Shuma-Gorath
Shuma-Gorath is an ancient, godlike, tentacled demon from Marvel Comics known for its immense mystical power and frequent clashes with Doctor Strange.
-
C.
Oger
Oger is a renowned Champagne-producing village in France’s Côte des Blancs, celebrated for its high-quality Chardonnay vineyards and prestigious Grand Cru status.
-
D.
Zahhak
Zahhak is a legendary tyrant king in Persian mythology, most famously depicted in Ferdowsi’s Shahnameh as a demonic ruler with serpents growing from his shoulders.
-
E.
Cacus
Cacus is a fire-breathing giant and notorious cattle-stealing monster from Roman mythology, best known for being slain by the hero Hercules.
- 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_69ca839481d48190b42b037e0d0f636c |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc66700fb48190874563e535f20437 |
completed | April 1, 2026, 12:27 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfba58e9ec81909141c516d05ac790 |
completed | April 3, 2026, 1:02 p.m. |
Created at: March 30, 2026, 6:57 p.m.