Triple
T17419762
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bab al-Amud |
E423579
|
entity |
| Predicate | hasPredecessorStructure |
P50156
|
FINISHED |
| Object | Roman gate |
—
|
LITERAL 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: Roman gate | Statement: [Bab al-Amud, hasPredecessorStructure, Roman gate]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPredecessorStructure Context triple: [Bab al-Amud, hasPredecessorStructure, Roman gate]
-
A.
hasPredecessorStructureFrom
chosen
Indicates that one structure existed or was established before another structure in a sequential or developmental order.
-
B.
hasPredecessorType
Indicates that one type is derived from, follows, or is based on another earlier or more fundamental type in a sequence or hierarchy.
-
C.
hasPredecessorGeneration
Indicates that one generation directly precedes another in a temporal or genealogical sequence.
-
D.
hasPredecessorRoleIn
Indicates that one role functioned earlier in time or sequence relative to another role within the same context or position.
-
E.
predecessorStateOf
Indicates that one state occurs immediately before and leads into another state in a sequence or process.
- F. None of above.
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_69d889d7d27c819088486ce3f0627fa1 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e44236419c8190a106748bca6f30cd |
completed | April 19, 2026, 2:47 a.m. |
| PD | Predicate disambiguation | batch_69e3b02e6cc88190986e85e64ce9383e |
completed | April 18, 2026, 4:24 p.m. |
Created at: April 10, 2026, 5:46 a.m.