Triple
T31881586
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Enkidu’s curse and lament |
E813896
|
entity |
| Predicate | occursInTablet |
P173003
|
FINISHED |
| Object | Tablet VII of the Standard Babylonian Epic of Gilgamesh |
—
|
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: Tablet VII of the Standard Babylonian Epic of Gilgamesh | Statement: [Enkidu’s curse and lament, occursInTablet, Tablet VII of the Standard Babylonian Epic of Gilgamesh]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: occursInTablet Context triple: [Enkidu’s curse and lament, occursInTablet, Tablet VII of the Standard Babylonian Epic of Gilgamesh]
-
A.
occursInDevice
Indicates that an event, process, or phenomenon takes place within or inside a specified device.
-
B.
hasFormFactor
Indicates that one entity possesses or is characterized by a particular physical or structural form factor defined by another entity.
-
C.
targetFormFactor
Indicates the specific physical configuration or design format that something is intended to be used with or fit into.
-
D.
isNotebookOf
Indicates that one entity is a notebook that belongs to, is used by, or is associated with another entity.
-
E.
supportsHandheldMode
Indicates that an entity is capable of operating or being used in a handheld mode.
- F. None of above. chosen
Provenance (4 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_69f348ed74bc81909846aaa6a3c7318c |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6b2d9aad88190a445f8f591cb19fc |
completed | May 3, 2026, 2:28 a.m. |
| PD | Predicate disambiguation | batch_69f6b14faf608190a25b977c0740729c |
completed | May 3, 2026, 2:22 a.m. |
| PDg | Predicate description generation | batch_69f6b21da77081908c5c015c4606d344 |
completed | May 3, 2026, 2:25 a.m. |
Created at: April 30, 2026, 11:56 p.m.